subject:"Re\: Simple request from chatGPT to write assembler program."

This isn't new; you are responsible for work you sign off on. It doesn't matter 
that your legal assistant drew up the brief; you are obligated to do due 
diligence and verify it.


From: IBM Mainframe Discussion List  on behalf of 
Steve Thompson 
Sent: Tuesday, September 5, 2023 5:27 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Legal Problems with ChatGPT [Was Re: Simple request from chatGPT to 
write assembler program.]

Here is a take-off on the forbes article which is from the Legal
Ethics Law 360 email list (I also get the transportation law
stuff too):


Insurance Coverage For ChatGPT Legal Fiasco: A Hypothetical
<https://www.law360.com/transportation/articles/1696764?nl_pk=d963732e-149d-4918-a703-34cd62053317_source=newsletter_medium=email_campaign=transportation_content=2023-07-21_main=1=0=24>

William Passannante at Anderson Kill draws on the recent case of
an attorney sanctioned by the Southern District of New York for
submitting a ChatGPT-authored brief to discuss what the insurance
coverage for the attorney's hypothetical claim might look like.


And I think this is the original case:


Attys Behind ChatGPT Fiasco Apologize To Client, 7 Judges
<https://www.law360.com/legalethics/articles/1696411?nl_pk=19259802-3c70-4a5b-a647-8dd625cabc30_source=newsletter_medium=email_campaign=legalethics_content=2023-07-06=0=0>

By Hailey Konnath

A pair of New York personal injury attorneys apologized Wednesday
to seven federal and state judges and to a client for submitting
a brief prepared by artificial intelligence that cited
nonexistent case law attributed to the judges, according to
copies of the letters filed in Manhattan federal court.

And there are now other articles over whether or not chatGPT can
defame a person or something like that... And something about the
case being remanded.. (my head hurts).


Steve Thompson



On 9/5/2023 5:11 PM, Mike Schwab wrote:
> https://www.forbes.com/sites/mollybohannon/2023/06/08/lawyer-used-chatgpt-in-court-and-cited-fake-cases-a-judge-is-considering-sanctions/
>
> On Tue, Sep 5, 2023 at 4:03 PM Bob Bridges  wrote:
>> Can't remember whether I read about it here or somewhere else, but 
>> apparently there was a recent episode in which a lawyer got an AI machine to 
>> write a legal brief for him.  It looked impressive, but it turned out the 
>> precedents the brief cited didn't exist; the AI made them up.  The judge 
>> fined the lawyer.
>>
>> ---
>> Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313
>>
>> /* The most important fundamental laws and facts of physical science have 
>> all been discovered, and these are now so firmly established that the 
>> possibility of their ever being supplemented in consequence of new 
>> discoveries is exceedingly remote.  -Abraham Albert Michelson in 1903 */
>>
>> -Original Message-
>> From: IBM Mainframe Discussion List  On Behalf Of 
>> Dean Kent
>> Sent: Tuesday, September 5, 2023 12:46
>>
>> I spent a bit of time playing with chatGPT to see what it could do.   So did 
>> my two sons - one an MS in biotech, the other a PhD in theoretical physics.  
>>   We all came to the same conclusion - chatGPT is a very, very good Google 
>> search that can filter many different possible 'answers' and come to one 
>> that is 'most likely' based on various factors.  It has little to no 
>> creativity or understanding of what it is asked to do. Not surprising, but 
>> different than what the popular press seems to say about it.
>>
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

There you go again, lying about what people believe. If you're referring to 
people who chose to plonk you, your right to speak does not confer an 
obligation to listen. They don't believe that they run the list, but they 
rightly believe that they run their own property.

From: IBM Mainframe Discussion List  on behalf of 
Bill Johnson <0047540adefe-dmarc-requ...@listserv.ua.edu>
Sent: Wednesday, September 6, 2023 12:15 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

In fact I’m not. Because I only respond to attacks from the TT. Many here 
actually fear the TT. (Terrible Twenty) The TT thinks they run the list. They 
don’t.

Like I’ve said a number of times, there are very few experts here. I’m not one. 
If you have an SMP/E question, you probably have a 60-70% chance of getting the 
correct answer from the TT. Whereas you’ve got 99.9% chance with Kurt 
Quackenbush. You probably have a 60% chance of getting the correct answer for 
z/OS internals from the TT & 99.9% from Mr. Relson.

Knowing who to trust 100% and who to fact check with the experts is probably 
the most important thing here. I know if I want hardware numbers from the 60’s 
& 70’s, you’re the man.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 11:47 AM, Seymour J Metz  
wrote:

> Putting down other people in this profession is the MO of guys like the 
> terrible twenty.

I hope that you are including yourself in that.

From: IBM Mainframe Discussion List  on behalf of 
Bill Johnson <0047540adefe-dmarc-requ...@listserv.ua.edu>
Sent: Wednesday, September 6, 2023 9:09 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Assembler is of little value and declining every year for most 
Installers/Systems Programmers not a part of ISVs. Which is the vast majority.

Putting down other people in this profession is the MO of guys like the 
terrible twenty. Who claim that if you don’t know or use assembler, you’re just 
an “Installer” and a second rate Systems Programmer.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 9:03 AM, Bernd Oppolzer 
 wrote:

What you are quoting (1., 2., 3.) are facts ... of course true, and
nothing to dispute about.
But your conclusions are wrong ... Assembler is of value anyway; Ray
Mullins DID say that.
For example for studying the outcome of translators and for performance
analysis etc.
IMO knowledge of Assembler is NEEDED, once you want to dig a little
deeper into machine architecture
and other related topics. The Assembler language opens the door for the
understanding of registers,
storage, addressing schemes, operation formats and so on ... that is:
the hardware.

IMO, you always seem to be forced to put down other people and their
skills; I don't understand why.
But what scares me most is that your constant use of words like
"dinosaurs" and "narcissists"
(and "idiots", BTW) in this discussions. And that's why I will not
answer to any more mails from you from now on.
Should have done so earlier, maybe.

Bernd

Am 06.09.2023 um 14:11 schrieb Bill Johnson:
> Everything I said about assembler has rung true.
>
> 1. The assembler listserv is nearly dead.
> 2. One of assemblers experts, Ray Mullins, stated unequivocally its market is 
> getting smaller and smaller and is a niche product.
> 3. Bernd said since 2005, there’s been little demand for assembler training.
>
> ...
>
> And the dinosaurs here trying so hard to not become extinct.
> Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it 
> makes them wrong and narcissists don’t like saying they were wrong.
>
> ...

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

91? That mean big bucks, and the "optimizing" compiler, which didn't have that 
problem, was chump change by comparison.

From: IBM Mainframe Discussion List  on behalf of 
Michael Stein 
Sent: Wednesday, September 6, 2023 6:45 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

On Wed, Sep 06, 2023 at 09:02:28PM +0200, Bernd Oppolzer wrote:
> IIRC, in the first years of HLLs, there were some debates that HLLs
> are not usable because of the poor code the compilers generated at that
> time. This was true even in the 1960s for the first versions of PL/1.

A lot later than that, try the 70s.  PL/1 F level subroutine calls did
a getmain/freemain for each subroutine call.  Too much overhead to call
even one subroutine for each of 30K records on a 360/91 & MVT.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

While PL/I F did a GETMAIN for every DSA, no subsequent compiler did. Starting 
with Version 1 Release 1, the runtime library for the "optimizing" and checkout 
compiler did a GETMAIN for an ISA and as long as it was large enough, 
subsequent calls used it as a stack. Only when a DSA didn't fit was there a 
GETMAIN for an additional stack segment. Exiting a block adjusted the stack but 
did not do a FREEMAIN of unused stack segments.

The net result was to save time at the expense of storage; unless you were 
storage constrain, it was a btter approach.


From: IBM Mainframe Discussion List  on behalf of 
Bernd Oppolzer 
Sent: Wednesday, September 6, 2023 11:13 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Am 07.09.2023 um 01:40 schrieb Leonard D Woren:
> Michael Stein wrote on 9/6/2023 3:45 PM:
>> [...] PL/1 F level subroutine calls did a getmain/freemain for each
>> subroutine call. Too much overhead to call even one subroutine for
>> each of 30K records on a 360/91 & MVT.
>
> Well, my recollection is that if you had only Static storage, no
> Automatic storage, it didn't do a GETMAIN.
> Or was that an enhancement in the new PL/I compiler?  Was that PLIX?
> Yeah, not using stuff for decades can cause memory fade.
>
>
> /Leonard
>

I first came into contact with PL/1 in the end of the 1980s at the
beforementionend insurance company.
At that time, they had the V2.3 optimizer (IIRC), and it produced pretty
amazing code. I was asked to
do PL/1 classes for the developers there. This company made (and still
makes) heavy use of automatic storage and tried to
code all modules "naturally reentrant", that is: no modified static
storage. So the problems with getmain/freemain
at procedure startup and end must have been long gone. That company
started with PL/1 in the beginning of the 1980s,
before that is was an ASSEMBLER only shop. (C came later, from 1992 on).

1992 (and 1994 again) I was asked to do a dump analysis class in another
PL/1 company. They indeed had

DEFEAULT RANGE(*) STATIC;

in almost every program. I didn't understand the reason at that time and
thought is was for dump reading,
because static variable (in the STATIC CSECT which is part of the load
module) are much easier to find than
auto variables (living in the stack). But now I have the impression that
this could have simply been a performance
issue in the beginning.

Kind regards

Bernd

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Monty the Mustang will be disappointed.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 9:25 PM, Matt Hogstrom  
wrote:

Sorry Dave but I’m skipping to Bill’s response.  

I recently blocked Bill's e-mail and don’t get to see his posts apart from 
people’s responses.  For those that might be interested … block 
0047540adefe-dmarc-requ...@listserv.ua.edu 
 which seems to be 
Bill’s address.  My inbox is cleaner except for the responses to him.  He 
always could deregister and re-register but then his intentions to disrupt 
would be obvious.  Bill, you were entertaining and now I’m just embarrassed for 
you.

Matt Hogstrom

“It may be cognitive, but, it ain’t intuitive."
— Hogstrom

> On Sep 6, 2023, at 9:29 AM, David Spiegel 
> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
> 
>> LOL, good find Dave. I love how in your head

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Am 07.09.2023 um 01:40 schrieb Leonard D Woren:

Michael Stein wrote on 9/6/2023 3:45 PM:
[...] PL/1 F level subroutine calls did a getmain/freemain for each 
subroutine call. Too much overhead to call even one subroutine for 
each of 30K records on a 360/91 & MVT.


Well, my recollection is that if you had only Static storage, no 
Automatic storage, it didn't do a GETMAIN.
Or was that an enhancement in the new PL/I compiler?  Was that PLIX?  
Yeah, not using stuff for decades can cause memory fade.



/Leonard



I first came into contact with PL/1 in the end of the 1980s at the 
beforementionend insurance company.
At that time, they had the V2.3 optimizer (IIRC), and it produced pretty 
amazing code. I was asked to
do PL/1 classes for the developers there. This company made (and still 
makes) heavy use of automatic storage and tried to
code all modules "naturally reentrant", that is: no modified static 
storage. So the problems with getmain/freemain
at procedure startup and end must have been long gone. That company 
started with PL/1 in the beginning of the 1980s,

before that is was an ASSEMBLER only shop. (C came later, from 1992 on).

1992 (and 1994 again) I was asked to do a dump analysis class in another 
PL/1 company. They indeed had


DEFEAULT RANGE(*) STATIC;

in almost every program. I didn't understand the reason at that time and 
thought is was for dump reading,
because static variable (in the STATIC CSECT which is part of the load 
module) are much easier to find than
auto variables (living in the stack). But now I have the impression that 
this could have simply been a performance

issue in the beginning.

Kind regards

Bernd

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Matt Hogstrom

Sorry Dave but I’m skipping to Bill’s response.  

I recently blocked Bill's e-mail and don’t get to see his posts apart from 
people’s responses.  For those that might be interested … block 
0047540adefe-dmarc-requ...@listserv.ua.edu 
 which seems to be 
Bill’s address.  My inbox is cleaner except for the responses to him.  He 
always could deregister and re-register but then his intentions to disrupt 
would be obvious.  Bill, you were entertaining and now I’m just embarrassed for 
you.

Matt Hogstrom

“It may be cognitive, but, it ain’t intuitive."
— Hogstrom

> On Sep 6, 2023, at 9:29 AM, David Spiegel 
> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
> 
>> LOL, good find Dave. I love how in your head

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Most businesses disagree with you and are spending billions to achieve.

https://www.accenture.com/us-en/services/ai-artificial-intelligence-index

Comparing 1973 to 2023 is like comparing a model T Ford to a space-X rocket.
Technological advances are coming faster & faster.

The phone in my hand has more computing power than the computer that put man on
the moon. By a large factor.

https://blog.adobe.com/en/publish/2022/11/08/fast-forward-comparing-1980s-supercomputer-to-modern-smartphone

I agree, it isn’t so much a new software development as it is massive storage,
incredible processing speed, & ability to put the results into a form the user
is requesting. But, there is some logic and machine learning involved. The next
decade will be amazing.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 7:31 PM, Leonard D Woren
wrote:

Bill Johnson wrote on 9/6/2023 6:27 AM:
> [...] AI is the future. [...]

FSV "future". Who remembers the "Parry" program from the early
1970s? At SAIL, later renamed to SU-AI. Oh, if you weren't on the
ARPAnet circa 1973, you probably never saw Parry. It was the first AI
program I knew about. I don't remember which famous computer science
guy said this, but there haven't been and will never be any
"significant breakthroughs" in AI -- all progress will be slow and
incremental. I say that recent apparent advances in AI are more due
to faster cheaper computers and storage, and now the Internet, than to
any new software tech.

/Leonard

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Steve Beaver

I tried Chathpt to write the prolog part of an assembler prolog.  It did not do 
badly but what it put out needed a little work but it was repairable 

Sent from my iPhone

No one said I could type with one thumb 

> On Sep 6, 2023, at 18:30, Leonard D Woren  wrote:
> 
> Bill Johnson wrote on 9/6/2023 6:27 AM:
>> [...]  AI is the future. [...]
> 
> FSV "future".  Who remembers the "Parry" program from the early 1970s?  At 
> SAIL, later renamed to SU-AI.  Oh, if you weren't on the ARPAnet circa 1973, 
> you probably never saw Parry.  It was the first AI program I knew about.  I 
> don't remember which famous computer science guy said this, but there haven't 
> been and will never be any "significant breakthroughs" in AI -- all progress 
> will be slow and incremental.  I say that recent apparent advances in AI are 
> more due to faster cheaper computers and storage, and now the Internet, than 
> to any new software tech.
> 
> 
> /Leonard
> 
> 
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Leonard D Woren


Michael Stein wrote on 9/6/2023 3:45 PM:
[...] PL/1 F level subroutine calls did a getmain/freemain for each 
subroutine call. Too much overhead to call even one subroutine for 
each of 30K records on a 360/91 & MVT.


Well, my recollection is that if you had only Static storage, no 
Automatic storage, it didn't do a GETMAIN.  Or was that an enhancement 
in the new PL/I compiler?  Was that PLIX?  Yeah, not using stuff for 
decades can cause memory fade.



/Leonard


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Leonard D Woren


Bill Johnson wrote on 9/6/2023 6:27 AM:

[...]  AI is the future. [...]


FSV "future".  Who remembers the "Parry" program from the early 
1970s?  At SAIL, later renamed to SU-AI.  Oh, if you weren't on the 
ARPAnet circa 1973, you probably never saw Parry.  It was the first AI 
program I knew about.  I don't remember which famous computer science 
guy said this, but there haven't been and will never be any 
"significant breakthroughs" in AI -- all progress will be slow and 
incremental.  I say that recent apparent advances in AI are more due 
to faster cheaper computers and storage, and now the Internet, than to 
any new software tech.



/Leonard


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Michael Stein

On Wed, Sep 06, 2023 at 09:02:28PM +0200, Bernd Oppolzer wrote:
> IIRC, in the first years of HLLs, there were some debates that HLLs
> are not usable because of the poor code the compilers generated at that
> time. This was true even in the 1960s for the first versions of PL/1.

A lot later than that, try the 70s.  PL/1 F level subroutine calls did
a getmain/freemain for each subroutine call.  Too much overhead to call
even one subroutine for each of 30K records on a 360/91 & MVT.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Because throughout over half my career ACF2 was the number 1 security package 
and RACF only had around 20% of the market. Medical Mutual, my longest time at 
any one employer used Top Secret. Most people who claim to be knowledgeable 
about the mainframe, would know ACF2 was the number 1 security package for most 
of the late 20th century. 


Sent from Yahoo Mail for iPhone


On Wednesday, September 6, 2023, 4:12 PM, Wayne Bickerdike  
wrote:

How can Bombastic Bill have worked all those years and never worked in a
RACF shop? VSE shops never had RACF, however, RACF has had the Lion's share
for years.

On Thu, Sep 7, 2023 at 5:32 AM Seymour J Metz  wrote:

> Yes, assemblers came first, but <
> https://en.wikipedia.org/wiki/Laning_and_Zierler_system> was well before
> FORTRAN. I' not sure whether to cite the earlier <
> https://en.wikipedia.org/wiki/Plankalk%C3%BCl>, as it was never
> implemented.
>
>
> 
> From: IBM Mainframe Discussion List  on behalf
> of Bernd Oppolzer 
> Sent: Wednesday, September 6, 2023 3:02 PM
> To: IBM-MAIN@LISTSERV.UA.EDU
> Subject: Re: Simple request from chatGPT to write assembler program.
>
> Ok ... not quire correct, but:
> the first ASSEMBLER languages go back to the years 1947 to 1951, if my
> sources are right;
> there was some sort of ASSEMBLER for the 701 (which was available in
> 1953, IIRC).
> The first HLL was Fortran, IMO, which should be 1956 ca.
> So there are some years in the 1950 time frame, where ASSEMBLER was the
> only choice;
> that's what I am talking about.
> IIRC, in the first years of HLLs, there were some debates that HLLs are
> not usable because of
> the poor code the compilers generated at that time. This was true even
> in the 1960s for the
> first versions of PL/1.
> Kind regards
> Bernd
>
>
> Am 06.09.2023 um 17:55 schrieb Seymour J Metz:
> >> because in the 1950s and 1960s,
> >> it was the only language we had.
> > ?
> >
> > COBOL
> > COMIT
> > FACT
> > FARGO
> > FORTRAN
> > IPL-V
> > LISP
> > PL/I
> > RPG
> > SNOBOL
> >
> >
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>


-- 
Wayne V. Bickerdike

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Wayne Bickerdike

How can Bombastic Bill have worked all those years and never worked in a
RACF shop? VSE shops never had RACF, however, RACF has had the Lion's share
for years.

On Thu, Sep 7, 2023 at 5:32 AM Seymour J Metz  wrote:

> Yes, assemblers came first, but <
> https://en.wikipedia.org/wiki/Laning_and_Zierler_system> was well before
> FORTRAN. I' not sure whether to cite the earlier <
> https://en.wikipedia.org/wiki/Plankalk%C3%BCl>, as it was never
> implemented.
>
>
> 
> From: IBM Mainframe Discussion List  on behalf
> of Bernd Oppolzer 
> Sent: Wednesday, September 6, 2023 3:02 PM
> To: IBM-MAIN@LISTSERV.UA.EDU
> Subject: Re: Simple request from chatGPT to write assembler program.
>
> Ok ... not quire correct, but:
> the first ASSEMBLER languages go back to the years 1947 to 1951, if my
> sources are right;
> there was some sort of ASSEMBLER for the 701 (which was available in
> 1953, IIRC).
> The first HLL was Fortran, IMO, which should be 1956 ca.
> So there are some years in the 1950 time frame, where ASSEMBLER was the
> only choice;
> that's what I am talking about.
> IIRC, in the first years of HLLs, there were some debates that HLLs are
> not usable because of
> the poor code the compilers generated at that time. This was true even
> in the 1960s for the
> first versions of PL/1.
> Kind regards
> Bernd
>
>
> Am 06.09.2023 um 17:55 schrieb Seymour J Metz:
> >> because in the 1950s and 1960s,
> >> it was the only language we had.
> > ?
> >
> > COBOL
> > COMIT
> > FACT
> > FARGO
> > FORTRAN
> > IPL-V
> > LISP
> > PL/I
> > RPG
> > SNOBOL
> >
> >
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>


-- 
Wayne V. Bickerdike

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Seymour J Metz

Yes, assemblers came first, but 
<https://en.wikipedia.org/wiki/Laning_and_Zierler_system> was well before  
FORTRAN. I' not sure whether to cite the earlier 
<https://en.wikipedia.org/wiki/Plankalk%C3%BCl>, as it was never implemented.



From: IBM Mainframe Discussion List  on behalf of 
Bernd Oppolzer 
Sent: Wednesday, September 6, 2023 3:02 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Ok ... not quire correct, but:
the first ASSEMBLER languages go back to the years 1947 to 1951, if my
sources are right;
there was some sort of ASSEMBLER for the 701 (which was available in
1953, IIRC).
The first HLL was Fortran, IMO, which should be 1956 ca.
So there are some years in the 1950 time frame, where ASSEMBLER was the
only choice;
that's what I am talking about.
IIRC, in the first years of HLLs, there were some debates that HLLs are
not usable because of
the poor code the compilers generated at that time. This was true even
in the 1960s for the
first versions of PL/1.
Kind regards
Bernd


Am 06.09.2023 um 17:55 schrieb Seymour J Metz:
>> because in the 1950s and 1960s,
>> it was the only language we had.
> ?
>
> COBOL
> COMIT
> FACT
> FARGO
> FORTRAN
> IPL-V
> LISP
> PL/I
> RPG
> SNOBOL
>
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Ok ... not quire correct, but:
the first ASSEMBLER languages go back to the years 1947 to 1951, if my 
sources are right;
there was some sort of ASSEMBLER for the 701 (which was available in 
1953, IIRC).

The first HLL was Fortran, IMO, which should be 1956 ca.
So there are some years in the 1950 time frame, where ASSEMBLER was the 
only choice;

that's what I am talking about.
IIRC, in the first years of HLLs, there were some debates that HLLs are 
not usable because of
the poor code the compilers generated at that time. This was true even 
in the 1960s for the

first versions of PL/1.
Kind regards
Bernd


Am 06.09.2023 um 17:55 schrieb Seymour J Metz:

because in the 1950s and 1960s,
it was the only language we had.

?

COBOL
COMIT
FACT
FARGO
FORTRAN
IPL-V
LISP
PL/I
RPG
SNOBOL




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

In fact I’m not. Because I only respond to attacks from the TT. Many here 
actually fear the TT. (Terrible Twenty) The TT thinks they run the list. They 
don’t.

Like I’ve said a number of times, there are very few experts here. I’m not one. 
If you have an SMP/E question, you probably have a 60-70% chance of getting the 
correct answer from the TT. Whereas you’ve got 99.9% chance with Kurt 
Quackenbush. You probably have a 60% chance of getting the correct answer for 
z/OS internals from the TT & 99.9% from Mr. Relson.

Knowing who to trust 100% and who to fact check with the experts is probably 
the most important thing here. I know if I want hardware numbers from the 60’s 
& 70’s, you’re the man.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 11:47 AM, Seymour J Metz  
wrote:

> Putting down other people in this profession is the MO of guys like the 
> terrible twenty.

I hope that you are including yourself in that.

From: IBM Mainframe Discussion List  on behalf of 
Bill Johnson <0047540adefe-dmarc-requ...@listserv.ua.edu>
Sent: Wednesday, September 6, 2023 9:09 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Assembler is of little value and declining every year for most 
Installers/Systems Programmers not a part of ISVs. Which is the vast majority.

Putting down other people in this profession is the MO of guys like the 
terrible twenty. Who claim that if you don’t know or use assembler, you’re just 
an “Installer” and a second rate Systems Programmer.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 9:03 AM, Bernd Oppolzer 
 wrote:

What you are quoting (1., 2., 3.) are facts ... of course true, and
nothing to dispute about.
But your conclusions are wrong ... Assembler is of value anyway; Ray
Mullins DID say that.
For example for studying the outcome of translators and for performance
analysis etc.
IMO knowledge of Assembler is NEEDED, once you want to dig a little
deeper into machine architecture
and other related topics. The Assembler language opens the door for the
understanding of registers,
storage, addressing schemes, operation formats and so on ... that is:
the hardware.

IMO, you always seem to be forced to put down other people and their
skills; I don't understand why.
But what scares me most is that your constant use of words like
"dinosaurs" and "narcissists"
(and "idiots", BTW) in this discussions. And that's why I will not
answer to any more mails from you from now on.
Should have done so earlier, maybe.

Bernd

Am 06.09.2023 um 14:11 schrieb Bill Johnson:
> Everything I said about assembler has rung true.
>
> 1. The assembler listserv is nearly dead.
> 2. One of assemblers experts, Ray Mullins, stated unequivocally its market is 
> getting smaller and smaller and is a niche product.
> 3. Bernd said since 2005, there’s been little demand for assembler training.
>
> ...
>
> And the dinosaurs here trying so hard to not become extinct.
> Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it 
> makes them wrong and narcissists don’t like saying they were wrong.
>
> ...

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Seymour J Metz

> because in the 1950s and 1960s,
> it was the only language we had.

?

COBOL
COMIT
FACT
FARGO
FORTRAN
IPL-V
LISP
PL/I
RPG
SNOBOL

From: IBM Mainframe Discussion List  on behalf of 
Bernd Oppolzer 
Sent: Wednesday, September 6, 2023 3:29 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Thanks a lot,

it would be always better to give even a very small ASSEMBLER program a
test run
instead of simply posting it to a public web site.
I will fix this on Wikipedia as soon as I can.

I'm not sure if ASSEMBLER should be used by humans :-) given this episode.
In fact, it was used in the past (heavily), because in the 1950s and
1960s, it was the only language we had.
And it is still used on Mainframes (some say: Mainframe Assembler is the
only usable Assembler, all others are not)
and as long as we have large code bases in Assembler, there is no other
way than supporting it
(and we have large code bases, this is what John Ehrman once told me ...
most customers who still have that
don't want to talk about it).

Anyway: the reasons to learn it (like: to understand the code produced
by other language translators better etc.
and to understand language translators, BTW) are very valid, and that's
what Ray Mullins (liebe Grüße)
tells in his papers, too, if I understand him right.

Another fun story:

Once a co-worker of mine (at the large insurance company mentioned
earlier) had a problem with IBM software,
and while communicating with IBM, he posted a bit of ASSEMBLER code
showing the error, and the answer of
IBM support was "Customer should not use ASSEMBLER" :-)

Kind regards
Bernd

Am 06.09.2023 um 05:44 schrieb Tom Brennan:
> Your sample assembled fine but abended 0C1.  I made some minor mods.
> Hope you don't mind my pretend German in the comments :)
>
> The biggest problem is trying to use R15 as a base.  That gets messed
> up by OPEN.  The other problem is LA instead of L when loading R13 for
> the return.  I mix those up a lot myself.
>
> https://www.mildredbrennan.com/mvs/hello.png
>
> P.S. My wife and I were in München last May.  Beautiful city and it
> was fun trying to understand the language based on a high-school class.
>
>
>
> On 9/5/2023 6:19 PM, Bernd Oppolzer wrote:
>> FWIW:
>>
>> ChatGPT could have used this ASSEMBLER program, which I posted some
>> years ago
>> to German Wikpedia ... this does not do the addition of two integers,
>> but instead it
>> is a simple Hello World program. In contrast to the program provided
>> by ChatGPT,
>> it has no errors (I hope) and it will work.
>>
>> https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER
>>
>>
>> Kind regards
>>
>> Bernd
>>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Tom Brennan

If you wrote that code on Wiki from scratch without ever assembling it, 
that's pretty amazing.  My method is to basically copy, modify, and let 
the computer find my problems - with lots of iterations.  It's just a 
different way to work I guess.


On 9/6/2023 12:29 AM, Bernd Oppolzer wrote:

Thanks a lot,

it would be always better to give even a very small ASSEMBLER program a 
test run

instead of simply posting it to a public web site.
I will fix this on Wikipedia as soon as I can.

I'm not sure if ASSEMBLER should be used by humans :-) given this episode.
In fact, it was used in the past (heavily), because in the 1950s and 
1960s, it was the only language we had.
And it is still used on Mainframes (some say: Mainframe Assembler is the 
only usable Assembler, all others are not)
and as long as we have large code bases in Assembler, there is no other 
way than supporting it
(and we have large code bases, this is what John Ehrman once told me ... 
most customers who still have that

don't want to talk about it).

Anyway: the reasons to learn it (like: to understand the code produced 
by other language translators better etc.
and to understand language translators, BTW) are very valid, and that's 
what Ray Mullins (liebe Grüße)

tells in his papers, too, if I understand him right.

Another fun story:

Once a co-worker of mine (at the large insurance company mentioned 
earlier) had a problem with IBM software,
and while communicating with IBM, he posted a bit of ASSEMBLER code 
showing the error, and the answer of

IBM support was "Customer should not use ASSEMBLER" :-)

Kind regards
Bernd


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Seymour J Metz

> Putting down other people in this profession is the MO of guys like the 
> terrible twenty.

I hope that you are including yourself in that.

From: IBM Mainframe Discussion List  on behalf of 
Bill Johnson <0047540adefe-dmarc-requ...@listserv.ua.edu>
Sent: Wednesday, September 6, 2023 9:09 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

Assembler is of little value and declining every year for most 
Installers/Systems Programmers not a part of ISVs. Which is the vast majority.

Putting down other people in this profession is the MO of guys like the 
terrible twenty. Who claim that if you don’t know or use assembler, you’re just 
an “Installer” and a second rate Systems Programmer.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 9:03 AM, Bernd Oppolzer 
 wrote:

What you are quoting (1., 2., 3.) are facts ... of course true, and
nothing to dispute about.
But your conclusions are wrong ... Assembler is of value anyway; Ray
Mullins DID say that.
For example for studying the outcome of translators and for performance
analysis etc.
IMO knowledge of Assembler is NEEDED, once you want to dig a little
deeper into machine architecture
and other related topics. The Assembler language opens the door for the
understanding of registers,
storage, addressing schemes, operation formats and so on ... that is:
the hardware.

IMO, you always seem to be forced to put down other people and their
skills; I don't understand why.
But what scares me most is that your constant use of words like
"dinosaurs" and "narcissists"
(and "idiots", BTW) in this discussions. And that's why I will not
answer to any more mails from you from now on.
Should have done so earlier, maybe.

Bernd

Am 06.09.2023 um 14:11 schrieb Bill Johnson:
> Everything I said about assembler has rung true.
>
> 1. The assembler listserv is nearly dead.
> 2. One of assemblers experts, Ray Mullins, stated unequivocally its market is 
> getting smaller and smaller and is a niche product.
> 3. Bernd said since 2005, there’s been little demand for assembler training.
>
> ...
>
> And the dinosaurs here trying so hard to not become extinct.
> Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it 
> makes them wrong and narcissists don’t like saying they were wrong.
>
> ...

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Since I’ve never worked in a RACF shop, ACF2 & Top Secret only, is this 
relevant? Or is your narcissism really strong today?
Do you know what a narcissist is? Because you’re textbook.


Sent from Yahoo Mail for iPhone


On Wednesday, September 6, 2023, 10:30 AM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
Do you know the meaning of "non sequitur"?
What is the connection between my attention to detail, your mother's 
career and your winning awards?
Now that you're busy boasting, why don't you also tell us which state 
gave you the awards?

Since you're the self-proclaimed expert on the relevance of Assembler, 
please explain how  an installer like yourself would create an ICHRDSNT 
Exit (with appropriate SMP/e control cards).

Regards,
David

On 2023-09-06 08:11, Bill Johnson wrote:
> LOL, good find Dave. I love how in your head I am. But, you won’t find many 
> grammar or spelling errors. My mom was a teacher. Dave has relegated himself 
> to spelling and grammar checks. Which takes me back to the state awards in 
> Algebra and Geometry I received. At the top in those subjects.
>
> Everything I said about assembler has rung true.
>
> 1. The assembler listserv is nearly dead.2. One of assemblers experts, Ray 
> Mullins, stated unequivocally its market is getting smaller and smaller and 
> is a niche product.3. Bernd said since 2005, there’s been little demand for 
> assembler training.
>
> Clearly assembler is not long for the mainframe world and just waiting for 
> the grim reaper to arrive. And the dinosaurs here trying so hard to not 
> become extinct.
>
> Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it 
> makes them wrong and narcissists don’t like saying they were wrong.
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 9:14 PM, David Spiegel 
> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
>
> Hi Bill,
> You said: "...Your comprehension of basic English are terrible. ..."
> Doorknob, it should have been "is terrible".
>
> Another case of the pot calling the kettle black.
> Open mouth, change feet.
>
> Regards,
> David
>
> On 2023-09-05 20:46, Bill Johnson wrote:
>> I never once said it would assemble or run. I can see why you guys went into 
>> IT. Your comprehension of basic English are terrible.
>>
>>
>> Sent from Yahoo Mail for iPhone
>>
>>
>> On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
>>  wrote:
>>
>> Oh that's funny!  Then what are these notes from you I found in my trash
>> folder?  Sounds like you were sure it would assemble and run perfectly,
>> and also be able to take over someone's job today.
>>
>>      Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
>>      of you assembler geniuses could test it.
>>
>>      Lol, how about going to chatgpt and asking the same question. So that
>>      cut and paste isn’t a factor.
>>
>>      What are you afraid of? That a computer can do what you do? That your
>>      “skills” aren’t all that impressive and can be automated away?
>>
>> On 9/5/2023 4:47 PM, Bill Johnson wrote:
>>> I never presented it as a working model.
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>>
>>
>>
>>
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread David Spiegel


Hi Bill,
Do you know the meaning of "non sequitur"?
What is the connection between my attention to detail, your mother's 
career and your winning awards?
Now that you're busy boasting, why don't you also tell us which state 
gave you the awards?


Since you're the self-proclaimed expert on the relevance of Assembler, 
please explain how  an installer like yourself would create an ICHRDSNT 
Exit (with appropriate SMP/e control cards).


Regards,
David

On 2023-09-06 08:11, Bill Johnson wrote:

LOL, good find Dave. I love how in your head I am. But, you won’t find many 
grammar or spelling errors. My mom was a teacher. Dave has relegated himself to 
spelling and grammar checks. Which takes me back to the state awards in Algebra 
and Geometry I received. At the top in those subjects.

Everything I said about assembler has rung true.

1. The assembler listserv is nearly dead.2. One of assemblers experts, Ray 
Mullins, stated unequivocally its market is getting smaller and smaller and is 
a niche product.3. Bernd said since 2005, there’s been little demand for 
assembler training.

Clearly assembler is not long for the mainframe world and just waiting for the 
grim reaper to arrive. And the dinosaurs here trying so hard to not become 
extinct.

Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it makes 
them wrong and narcissists don’t like saying they were wrong.

Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 9:14 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
You said: "...Your comprehension of basic English are terrible. ..."
Doorknob, it should have been "is terrible".

Another case of the pot calling the kettle black.
Open mouth, change feet.

Regards,
David

On 2023-09-05 20:46, Bill Johnson wrote:

I never once said it would assemble or run. I can see why you guys went into 
IT. Your comprehension of basic English are terrible.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
 wrote:

Oh that's funny!  Then what are these notes from you I found in my trash
folder?  Sounds like you were sure it would assemble and run perfectly,
and also be able to take over someone's job today.

     Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
     of you assembler geniuses could test it.

     Lol, how about going to chatgpt and asking the same question. So that
     cut and paste isn’t a factor.

     What are you afraid of? That a computer can do what you do? That your
     “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:

I never presented it as a working model.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I’m betting Google’s chatbot is better. I haven’t tried it out yet. AI is the 
future. Assembler is not.


Sent from Yahoo Mail for iPhone


On Wednesday, September 6, 2023, 9:24 AM, Clem Clarke 
 wrote:

ChatGPT says that that it is a few years out of date often when you ask 
a "political" type question.

So I have been experimenting with Google's AI - Bard.Google.com. And I 
like it.

Recently, I have asked it about some programming.  Like "please code 
this:"  It isn't always accurate, however if often gives a different way 
of looking at a problem.

For example, based on the 40 year old Jol Panel instruction,  I have 
been developing a universal Panel or Form instruction that works in 
MVS/Zos, Windows and Linux.  I asked Bard about setting environment 
variables at the CURRENT level, and it suggested stuffing the keyboard 
with SET statements.  And it sort of worked, except it wouldn't work in 
an Windows BAT file - the keyboard and the next statement in the BAT 
file got all tangled up!  Ce la vie!

Anyway, it is all happening - although somewhat slowly.  Where, for 
example, do you store the results of a form so that a Clist can examine 
the results?  Or can a Rexx program use the Panel? And so on!

Clem

Dean Kent wrote:
> Which brings up another 'interesting' anecdote.   I used chatGPT to 
> 'write' a set of bylaws for a new non-profit for a youth sports 
> club.   I asked it over a dozen times with different wording, and it 
> came back with a wide variety of results - some that were long and 
> included many sections, and others that were short and included only 
> what might be considered 'necessary' sections.    I have a friend who 
> is an attorney, and he sent me the template that LexisNexis 
> provides.   It had a lot more content, some which the IRS now 
> indicates is 'preferred' or even required.    So I ended up using the 
> template since I could just remove or ignore sections that weren't 
> pertinent.   The template also had a variety of options (variables, if 
> you will) for wording depending on, for example, if the corporation 
> has a CEO or President and whether board officers can also be 
> corporate executives, etc.
>
> That caused me to make the decision that I would not consider using 
> chatGPT for creating legal documents.   Again, YMMV.
>
> On 9/5/2023 12:27 PM, Steve Thompson wrote:
>> And so we can now understand that when a paralegal or newly minted 
>> attorney uses it to find case law for points and authorities, it will 
>> will make them up to match what was being searched for when it 
>> prepares a motion it was asked for using the results of the search.
>>
>> And some attorneys got a judge quite angry with them when they didn't 
>> tell the court this, but the opposing council pointed out they could 
>> not find any such case listed in the pleadings/motion. Then the 
>> judge's people also could not find same This is the kind of thing 
>> that concerns me about AI today. Once it has been taught enough to 
>> learn on its own
>>
>> Steve Thompson
>>
>> On 9/5/2023 12:46 PM, Dean Kent wrote:
>>> I spent a bit of time playing with chatGPT to see what it could 
>>> do.   So did my two sons - one an MS in biotech, the other a PhD in 
>>> theoretical physics.    We all came to the same conclusion - chatGPT 
>>> is a very, very good Google search that can filter many different 
>>> possible 'answers' and come to one that is 'most likely' based on 
>>> various factors.  It has little to no creativity or understanding of 
>>> what it is asked to do.   Not surprising, but different than what 
>>> the popular press seems to say about it.
>>>
>>> One of my questions was to write a simple sort routine in HLASM. It 
>>> came back with a template containing the entry/exit code, and then a 
>>> comment *insert sort routine here*.    After doing that with many 
>>> different simple tasks, I came to the conclusion that the problem 
>>> chatGPT has with assembler (but not with C, Python, Java, etc.) is 
>>> that there are so few searchable examples of code in assembler.    
>>> So the quality of the results, for any question, depends upon what 
>>> exists out on the Internet.   Again, not surprising.
>>>
>>> As another example, I have an interest in what is called 'historical 
>>> analysis'.   There are a number of books on the subject, so I asked 
>>> chatGPT to compare/contrast two of the books.   Then two other 
>>> books, etc.    In literally every case it came back with the same 
>>> introductory text and conclusion - but inserted a couple of 
>>> paragraphs that was similar to a book review for each book and 
>>> compared the 'differences'.   Not very impressed.
>>>
>>> My PhD son uses it to find obscure hypotheses and formulas that 
>>> would otherwise require a great many hours (or days) of searching.   
>>> My MS son uses it in a similar fashion to ferret out alternative 
>>> options for the various cell growing and protein extraction for his 
>>> job.   A very

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Clem Clarke

ChatGPT says that that it is a few years out of date often when you ask 
a "political" type question.


So I have been experimenting with Google's AI - Bard.Google.com. And I 
like it.


Recently, I have asked it about some programming.  Like "please code 
this:"  It isn't always accurate, however if often gives a different way 
of looking at a problem.


For example, based on the 40 year old Jol Panel instruction,  I have 
been developing a universal Panel or Form instruction that works in 
MVS/Zos, Windows and Linux.  I asked Bard about setting environment 
variables at the CURRENT level, and it suggested stuffing the keyboard 
with SET statements.  And it sort of worked, except it wouldn't work in 
an Windows BAT file - the keyboard and the next statement in the BAT 
file got all tangled up!  Ce la vie!


Anyway, it is all happening - although somewhat slowly.  Where, for 
example, do you store the results of a form so that a Clist can examine 
the results?  Or can a Rexx program use the Panel? And so on!


Clem

Dean Kent wrote:
Which brings up another 'interesting' anecdote.   I used chatGPT to 
'write' a set of bylaws for a new non-profit for a youth sports 
club.   I asked it over a dozen times with different wording, and it 
came back with a wide variety of results - some that were long and 
included many sections, and others that were short and included only 
what might be considered 'necessary' sections.    I have a friend who 
is an attorney, and he sent me the template that LexisNexis 
provides.   It had a lot more content, some which the IRS now 
indicates is 'preferred' or even required.    So I ended up using the 
template since I could just remove or ignore sections that weren't 
pertinent.   The template also had a variety of options (variables, if 
you will) for wording depending on, for example, if the corporation 
has a CEO or President and whether board officers can also be 
corporate executives, etc.


That caused me to make the decision that I would not consider using 
chatGPT for creating legal documents.   Again, YMMV.


On 9/5/2023 12:27 PM, Steve Thompson wrote:
And so we can now understand that when a paralegal or newly minted 
attorney uses it to find case law for points and authorities, it will 
will make them up to match what was being searched for when it 
prepares a motion it was asked for using the results of the search.


And some attorneys got a judge quite angry with them when they didn't 
tell the court this, but the opposing council pointed out they could 
not find any such case listed in the pleadings/motion. Then the 
judge's people also could not find same This is the kind of thing 
that concerns me about AI today. Once it has been taught enough to 
learn on its own


Steve Thompson

On 9/5/2023 12:46 PM, Dean Kent wrote:
I spent a bit of time playing with chatGPT to see what it could 
do.   So did my two sons - one an MS in biotech, the other a PhD in 
theoretical physics.    We all came to the same conclusion - chatGPT 
is a very, very good Google search that can filter many different 
possible 'answers' and come to one that is 'most likely' based on 
various factors.  It has little to no creativity or understanding of 
what it is asked to do.   Not surprising, but different than what 
the popular press seems to say about it.


One of my questions was to write a simple sort routine in HLASM. It 
came back with a template containing the entry/exit code, and then a 
comment *insert sort routine here*.    After doing that with many 
different simple tasks, I came to the conclusion that the problem 
chatGPT has with assembler (but not with C, Python, Java, etc.) is 
that there are so few searchable examples of code in assembler.    
So the quality of the results, for any question, depends upon what 
exists out on the Internet.   Again, not surprising.


As another example, I have an interest in what is called 'historical 
analysis'.   There are a number of books on the subject, so I asked 
chatGPT to compare/contrast two of the books.   Then two other 
books, etc.    In literally every case it came back with the same 
introductory text and conclusion - but inserted a couple of 
paragraphs that was similar to a book review for each book and 
compared the 'differences'.   Not very impressed.


My PhD son uses it to find obscure hypotheses and formulas that 
would otherwise require a great many hours (or days) of searching.   
My MS son uses it in a similar fashion to ferret out alternative 
options for the various cell growing and protein extraction for his 
job.   A very useful tool, but not yet SkyNet...


YMMV.

On 9/5/2023 9:36 AM, Bill Johnson wrote:
We are all retired. The other 2 went before me. I went in 
July 2022. You’re an idiot regardless. What are you afraid of? That 
a computer can do what you do? That your “skills” aren’t all that 
impressive and can be automated away?



Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM,

Re: Simple request from chatGPT to write assembler program.

Lol, it pays to do thorough research. 1818 it began.

https://www.cambridge.org/core/journals/legal-information-management/article/lexisnexis-the-future-of-law-since-1818/08BFF6F4025EB3800E2E44681CA6025C




Sent from Yahoo Mail for iPhone


On Wednesday, September 6, 2023, 9:05 AM, Joe Monk  wrote:

"LexisNexis is over 200 years old..."

Bull. LexisNexis was started by a lawyer in 1956...

Joe

On Wed, Sep 6, 2023 at 7:57 AM Bill Johnson <
0047540adefe-dmarc-requ...@listserv.ua.edu> wrote:

> Shocking, LexisNexis is over 200 years old and is designed specifically
> for legal purposes. ChatGPT is less than a year old and isn’t designed
> (yet) for the legal profession.
>
> Good choice picking the LexisNexis one.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Wednesday, September 6, 2023, 8:48 AM, Dean Kent 
> wrote:
>
> Which brings up another 'interesting' anecdote.  I used chatGPT to
> 'write' a set of bylaws for a new non-profit for a youth sports club.
> I asked it over a dozen times with different wording, and it came back
> with a wide variety of results - some that were long and included many
> sections, and others that were short and included only what might be
> considered 'necessary' sections.    I have a friend who is an attorney,
> and he sent me the template that LexisNexis provides.  It had a lot
> more content, some which the IRS now indicates is 'preferred' or even
> required.    So I ended up using the template since I could just remove
> or ignore sections that weren't pertinent.  The template also had a
> variety of options (variables, if you will) for wording depending on,
> for example, if the corporation has a CEO or President and whether board
> officers can also be corporate executives, etc.
>
> That caused me to make the decision that I would not consider using
> chatGPT for creating legal documents.  Again, YMMV.
>
> On 9/5/2023 12:27 PM, Steve Thompson wrote:
> > And so we can now understand that when a paralegal or newly minted
> > attorney uses it to find case law for points and authorities, it will
> > will make them up to match what was being searched for when it
> > prepares a motion it was asked for using the results of the search.
> >
> > And some attorneys got a judge quite angry with them when they didn't
> > tell the court this, but the opposing council pointed out they could
> > not find any such case listed in the pleadings/motion. Then the
> > judge's people also could not find same This is the kind of thing
> > that concerns me about AI today. Once it has been taught enough to
> > learn on its own
> >
> > Steve Thompson
> >
> > On 9/5/2023 12:46 PM, Dean Kent wrote:
> >> I spent a bit of time playing with chatGPT to see what it could do.
> >> So did my two sons - one an MS in biotech, the other a PhD in
> >> theoretical physics.    We all came to the same conclusion - chatGPT
> >> is a very, very good Google search that can filter many different
> >> possible 'answers' and come to one that is 'most likely' based on
> >> various factors.  It has little to no creativity or understanding of
> >> what it is asked to do.  Not surprising, but different than what the
> >> popular press seems to say about it.
> >>
> >> One of my questions was to write a simple sort routine in HLASM. It
> >> came back with a template containing the entry/exit code, and then a
> >> comment *insert sort routine here*.    After doing that with many
> >> different simple tasks, I came to the conclusion that the problem
> >> chatGPT has with assembler (but not with C, Python, Java, etc.) is
> >> that there are so few searchable examples of code in assembler.    So
> >> the quality of the results, for any question, depends upon what
> >> exists out on the Internet.  Again, not surprising.
> >>
> >> As another example, I have an interest in what is called 'historical
> >> analysis'.  There are a number of books on the subject, so I asked
> >> chatGPT to compare/contrast two of the books.  Then two other books,
> >> etc.    In literally every case it came back with the same
> >> introductory text and conclusion - but inserted a couple of
> >> paragraphs that was similar to a book review for each book and
> >> compared the 'differences'.  Not very impressed.
> >>
> >> My PhD son uses it to find obscure hypotheses and formulas that would
> >> otherwise require a great many hours (or days) of searching.  My MS
> >> son uses it in a similar fashion to ferret out alternative options
> >> for the various cell growing and protein extraction for his job.  A
> >> very useful tool, but not yet SkyNet...
> >>
> >> YMMV.
> >>
> >> On 9/5/2023 9:36 AM, Bill Johnson wrote:
> >>> We are all retired. The other 2 went before me. I went in July 2022.
> >>> You’re an idiot regardless. What are you afraid of? That a computer
> >>> can do what you do? That your “skills” aren’t all that impressive
> >>> and can be automated away?
> >>>
> >>>
> >>> Sent from Yahoo Mail for iPhone
> >>>
> >>>
> >>> On Tuesday,

Re: Simple request from chatGPT to write assembler program.

Assembler is of little value and declining every year for most 
Installers/Systems Programmers not a part of ISVs. Which is the vast majority.

Putting down other people in this profession is the MO of guys like the 
terrible twenty. Who claim that if you don’t know or use assembler, you’re just 
an “Installer” and a second rate Systems Programmer.

Sent from Yahoo Mail for iPhone

On Wednesday, September 6, 2023, 9:03 AM, Bernd Oppolzer 
 wrote:

What you are quoting (1., 2., 3.) are facts ... of course true, and 
nothing to dispute about.
But your conclusions are wrong ... Assembler is of value anyway; Ray 
Mullins DID say that.
For example for studying the outcome of translators and for performance 
analysis etc.
IMO knowledge of Assembler is NEEDED, once you want to dig a little 
deeper into machine architecture
and other related topics. The Assembler language opens the door for the 
understanding of registers,
storage, addressing schemes, operation formats and so on ... that is: 
the hardware.

IMO, you always seem to be forced to put down other people and their 
skills; I don't understand why.
But what scares me most is that your constant use of words like 
"dinosaurs" and "narcissists"
(and "idiots", BTW) in this discussions. And that's why I will not 
answer to any more mails from you from now on.
Should have done so earlier, maybe.

Bernd

Am 06.09.2023 um 14:11 schrieb Bill Johnson:
> Everything I said about assembler has rung true.
>
> 1. The assembler listserv is nearly dead.
> 2. One of assemblers experts, Ray Mullins, stated unequivocally its market is 
> getting smaller and smaller and is a niche product.
> 3. Bernd said since 2005, there’s been little demand for assembler training.
>
> ...
>
> And the dinosaurs here trying so hard to not become extinct.
> Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it 
> makes them wrong and narcissists don’t like saying they were wrong.
>
> ...

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Joe Monk

"LexisNexis is over 200 years old..."

Bull. LexisNexis was started by a lawyer in 1956...

Joe

On Wed, Sep 6, 2023 at 7:57 AM Bill Johnson <
0047540adefe-dmarc-requ...@listserv.ua.edu> wrote:

> Shocking, LexisNexis is over 200 years old and is designed specifically
> for legal purposes. ChatGPT is less than a year old and isn’t designed
> (yet) for the legal profession.
>
> Good choice picking the LexisNexis one.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Wednesday, September 6, 2023, 8:48 AM, Dean Kent 
> wrote:
>
> Which brings up another 'interesting' anecdote.   I used chatGPT to
> 'write' a set of bylaws for a new non-profit for a youth sports club.
> I asked it over a dozen times with different wording, and it came back
> with a wide variety of results - some that were long and included many
> sections, and others that were short and included only what might be
> considered 'necessary' sections.I have a friend who is an attorney,
> and he sent me the template that LexisNexis provides.   It had a lot
> more content, some which the IRS now indicates is 'preferred' or even
> required.So I ended up using the template since I could just remove
> or ignore sections that weren't pertinent.   The template also had a
> variety of options (variables, if you will) for wording depending on,
> for example, if the corporation has a CEO or President and whether board
> officers can also be corporate executives, etc.
>
> That caused me to make the decision that I would not consider using
> chatGPT for creating legal documents.   Again, YMMV.
>
> On 9/5/2023 12:27 PM, Steve Thompson wrote:
> > And so we can now understand that when a paralegal or newly minted
> > attorney uses it to find case law for points and authorities, it will
> > will make them up to match what was being searched for when it
> > prepares a motion it was asked for using the results of the search.
> >
> > And some attorneys got a judge quite angry with them when they didn't
> > tell the court this, but the opposing council pointed out they could
> > not find any such case listed in the pleadings/motion. Then the
> > judge's people also could not find same This is the kind of thing
> > that concerns me about AI today. Once it has been taught enough to
> > learn on its own
> >
> > Steve Thompson
> >
> > On 9/5/2023 12:46 PM, Dean Kent wrote:
> >> I spent a bit of time playing with chatGPT to see what it could do.
> >> So did my two sons - one an MS in biotech, the other a PhD in
> >> theoretical physics.We all came to the same conclusion - chatGPT
> >> is a very, very good Google search that can filter many different
> >> possible 'answers' and come to one that is 'most likely' based on
> >> various factors.  It has little to no creativity or understanding of
> >> what it is asked to do.   Not surprising, but different than what the
> >> popular press seems to say about it.
> >>
> >> One of my questions was to write a simple sort routine in HLASM. It
> >> came back with a template containing the entry/exit code, and then a
> >> comment *insert sort routine here*.After doing that with many
> >> different simple tasks, I came to the conclusion that the problem
> >> chatGPT has with assembler (but not with C, Python, Java, etc.) is
> >> that there are so few searchable examples of code in assembler.So
> >> the quality of the results, for any question, depends upon what
> >> exists out on the Internet.   Again, not surprising.
> >>
> >> As another example, I have an interest in what is called 'historical
> >> analysis'.   There are a number of books on the subject, so I asked
> >> chatGPT to compare/contrast two of the books.   Then two other books,
> >> etc.In literally every case it came back with the same
> >> introductory text and conclusion - but inserted a couple of
> >> paragraphs that was similar to a book review for each book and
> >> compared the 'differences'.   Not very impressed.
> >>
> >> My PhD son uses it to find obscure hypotheses and formulas that would
> >> otherwise require a great many hours (or days) of searching.   My MS
> >> son uses it in a similar fashion to ferret out alternative options
> >> for the various cell growing and protein extraction for his job.   A
> >> very useful tool, but not yet SkyNet...
> >>
> >> YMMV.
> >>
> >> On 9/5/2023 9:36 AM, Bill Johnson wrote:
> >>> We are all retired. The other 2 went before me. I went in July 2022.
> >>> You’re an idiot regardless. What are you afraid of? That a computer
> >>> can do what you do? That your “skills” aren’t all that impressive
> >>> and can be automated away?
> >>>
> >>>
> >>> Sent from Yahoo Mail for iPhone
> >>>
> >>>
> >>> On Tuesday, September 5, 2023, 12:25 PM, David Spiegel
> >>> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
> >>>
> >>> Hi Bill,
> >>> I have a better idea.
> >>> Why don't you and the 2 buddies who helped you modify the IEFUSI fix
> >>> it?
> >>> Probably because you don't have the

Re: Simple request from chatGPT to write assembler program.

What you are quoting (1., 2., 3.) are facts ... of course true, and 
nothing to dispute about.
But your conclusions are wrong ... Assembler is of value anyway; Ray 
Mullins DID say that.
For example for studying the outcome of translators and for performance 
analysis etc.
IMO knowledge of Assembler is NEEDED, once you want to dig a little 
deeper into machine architecture
and other related topics. The Assembler language opens the door for the 
understanding of registers,
storage, addressing schemes, operation formats and so on ... that is: 
the hardware.


IMO, you always seem to be forced to put down other people and their 
skills; I don't understand why.
But what scares me most is that your constant use of words like 
"dinosaurs" and "narcissists"
(and "idiots", BTW) in this discussions. And that's why I will not 
answer to any more mails from you from now on.

Should have done so earlier, maybe.

Bernd


Am 06.09.2023 um 14:11 schrieb Bill Johnson:

Everything I said about assembler has rung true.

1. The assembler listserv is nearly dead.
2. One of assemblers experts, Ray Mullins, stated unequivocally its market is 
getting smaller and smaller and is a niche product.
3. Bernd said since 2005, there’s been little demand for assembler training.

...

And the dinosaurs here trying so hard to not become extinct.
Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it makes 
them wrong and narcissists don’t like saying they were wrong.

...


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Shocking, LexisNexis is over 200 years old and is designed specifically for 
legal purposes. ChatGPT is less than a year old and isn’t designed (yet) for 
the legal profession.

Good choice picking the LexisNexis one.


Sent from Yahoo Mail for iPhone


On Wednesday, September 6, 2023, 8:48 AM, Dean Kent  wrote:

Which brings up another 'interesting' anecdote.   I used chatGPT to 
'write' a set of bylaws for a new non-profit for a youth sports club.   
I asked it over a dozen times with different wording, and it came back 
with a wide variety of results - some that were long and included many 
sections, and others that were short and included only what might be 
considered 'necessary' sections.    I have a friend who is an attorney, 
and he sent me the template that LexisNexis provides.   It had a lot 
more content, some which the IRS now indicates is 'preferred' or even 
required.    So I ended up using the template since I could just remove 
or ignore sections that weren't pertinent.   The template also had a 
variety of options (variables, if you will) for wording depending on, 
for example, if the corporation has a CEO or President and whether board 
officers can also be corporate executives, etc.

That caused me to make the decision that I would not consider using 
chatGPT for creating legal documents.   Again, YMMV.

On 9/5/2023 12:27 PM, Steve Thompson wrote:
> And so we can now understand that when a paralegal or newly minted 
> attorney uses it to find case law for points and authorities, it will 
> will make them up to match what was being searched for when it 
> prepares a motion it was asked for using the results of the search.
>
> And some attorneys got a judge quite angry with them when they didn't 
> tell the court this, but the opposing council pointed out they could 
> not find any such case listed in the pleadings/motion. Then the 
> judge's people also could not find same This is the kind of thing 
> that concerns me about AI today. Once it has been taught enough to 
> learn on its own
>
> Steve Thompson
>
> On 9/5/2023 12:46 PM, Dean Kent wrote:
>> I spent a bit of time playing with chatGPT to see what it could do.   
>> So did my two sons - one an MS in biotech, the other a PhD in 
>> theoretical physics.    We all came to the same conclusion - chatGPT 
>> is a very, very good Google search that can filter many different 
>> possible 'answers' and come to one that is 'most likely' based on 
>> various factors.  It has little to no creativity or understanding of 
>> what it is asked to do.   Not surprising, but different than what the 
>> popular press seems to say about it.
>>
>> One of my questions was to write a simple sort routine in HLASM. It 
>> came back with a template containing the entry/exit code, and then a 
>> comment *insert sort routine here*.    After doing that with many 
>> different simple tasks, I came to the conclusion that the problem 
>> chatGPT has with assembler (but not with C, Python, Java, etc.) is 
>> that there are so few searchable examples of code in assembler.    So 
>> the quality of the results, for any question, depends upon what 
>> exists out on the Internet.   Again, not surprising.
>>
>> As another example, I have an interest in what is called 'historical 
>> analysis'.   There are a number of books on the subject, so I asked 
>> chatGPT to compare/contrast two of the books.   Then two other books, 
>> etc.    In literally every case it came back with the same 
>> introductory text and conclusion - but inserted a couple of 
>> paragraphs that was similar to a book review for each book and 
>> compared the 'differences'.   Not very impressed.
>>
>> My PhD son uses it to find obscure hypotheses and formulas that would 
>> otherwise require a great many hours (or days) of searching.   My MS 
>> son uses it in a similar fashion to ferret out alternative options 
>> for the various cell growing and protein extraction for his job.   A 
>> very useful tool, but not yet SkyNet...
>>
>> YMMV.
>>
>> On 9/5/2023 9:36 AM, Bill Johnson wrote:
>>> We are all retired. The other 2 went before me. I went in July 2022. 
>>> You’re an idiot regardless. What are you afraid of? That a computer 
>>> can do what you do? That your “skills” aren’t all that impressive 
>>> and can be automated away?
>>>
>>>
>>> Sent from Yahoo Mail for iPhone
>>>
>>>
>>> On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
>>> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
>>>
>>> Hi Bill,
>>> I have a better idea.
>>> Why don't you and the 2 buddies who helped you modify the IEFUSI fix 
>>> it?
>>> Probably because you don't have the wherewithal (even with 2 helpers).
>>>
>>> Regards,
>>> David
>>>
>>> On 2023-09-05 12:04, Bill Johnson wrote:
 Lol, how about going to chatgpt and asking the same question. So 
 that cut and paste isn’t a factor.


 Sent from Yahoo Mail for iPhone


 On Tuesday, September 5, 2023, 12:02 PM, David Spiegel

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Dean Kent

Which brings up another 'interesting' anecdote.   I used chatGPT to 
'write' a set of bylaws for a new non-profit for a youth sports club.   
I asked it over a dozen times with different wording, and it came back 
with a wide variety of results - some that were long and included many 
sections, and others that were short and included only what might be 
considered 'necessary' sections.    I have a friend who is an attorney, 
and he sent me the template that LexisNexis provides.   It had a lot 
more content, some which the IRS now indicates is 'preferred' or even 
required.    So I ended up using the template since I could just remove 
or ignore sections that weren't pertinent.   The template also had a 
variety of options (variables, if you will) for wording depending on, 
for example, if the corporation has a CEO or President and whether board 
officers can also be corporate executives, etc.


That caused me to make the decision that I would not consider using 
chatGPT for creating legal documents.   Again, YMMV.


On 9/5/2023 12:27 PM, Steve Thompson wrote:
And so we can now understand that when a paralegal or newly minted 
attorney uses it to find case law for points and authorities, it will 
will make them up to match what was being searched for when it 
prepares a motion it was asked for using the results of the search.


And some attorneys got a judge quite angry with them when they didn't 
tell the court this, but the opposing council pointed out they could 
not find any such case listed in the pleadings/motion. Then the 
judge's people also could not find same This is the kind of thing 
that concerns me about AI today. Once it has been taught enough to 
learn on its own


Steve Thompson

On 9/5/2023 12:46 PM, Dean Kent wrote:
I spent a bit of time playing with chatGPT to see what it could do.   
So did my two sons - one an MS in biotech, the other a PhD in 
theoretical physics.    We all came to the same conclusion - chatGPT 
is a very, very good Google search that can filter many different 
possible 'answers' and come to one that is 'most likely' based on 
various factors.  It has little to no creativity or understanding of 
what it is asked to do.   Not surprising, but different than what the 
popular press seems to say about it.


One of my questions was to write a simple sort routine in HLASM. It 
came back with a template containing the entry/exit code, and then a 
comment *insert sort routine here*.    After doing that with many 
different simple tasks, I came to the conclusion that the problem 
chatGPT has with assembler (but not with C, Python, Java, etc.) is 
that there are so few searchable examples of code in assembler.    So 
the quality of the results, for any question, depends upon what 
exists out on the Internet.   Again, not surprising.


As another example, I have an interest in what is called 'historical 
analysis'.   There are a number of books on the subject, so I asked 
chatGPT to compare/contrast two of the books.   Then two other books, 
etc.    In literally every case it came back with the same 
introductory text and conclusion - but inserted a couple of 
paragraphs that was similar to a book review for each book and 
compared the 'differences'.   Not very impressed.


My PhD son uses it to find obscure hypotheses and formulas that would 
otherwise require a great many hours (or days) of searching.   My MS 
son uses it in a similar fashion to ferret out alternative options 
for the various cell growing and protein extraction for his job.   A 
very useful tool, but not yet SkyNet...


YMMV.

On 9/5/2023 9:36 AM, Bill Johnson wrote:
We are all retired. The other 2 went before me. I went in July 2022. 
You’re an idiot regardless. What are you afraid of? That a computer 
can do what you do? That your “skills” aren’t all that impressive 
and can be automated away?



Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:


Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the IEFUSI fix 
it?

Probably because you don't have the wherewithal (even with 2 helpers).

Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:
Lol, how about going to chatgpt and asking the same question. So 
that cut and paste isn’t a factor.



Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:


Hi Steve,
It won't. The first executable statement is missing a comma between
operands.

Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one reason or
another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being 
used.


Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.

Re: Simple request from chatGPT to write assembler program.

LOL, good find Dave. I love how in your head I am. But, you won’t find many 
grammar or spelling errors. My mom was a teacher. Dave has relegated himself to 
spelling and grammar checks. Which takes me back to the state awards in Algebra 
and Geometry I received. At the top in those subjects.

Everything I said about assembler has rung true.

1. The assembler listserv is nearly dead.2. One of assemblers experts, Ray 
Mullins, stated unequivocally its market is getting smaller and smaller and is 
a niche product.3. Bernd said since 2005, there’s been little demand for 
assembler training.

Clearly assembler is not long for the mainframe world and just waiting for the 
grim reaper to arrive. And the dinosaurs here trying so hard to not become 
extinct.

Notice how the 20-30 experts can’t say, Bill Johnson is right. Because it makes 
them wrong and narcissists don’t like saying they were wrong.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 9:14 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
You said: "...Your comprehension of basic English are terrible. ..."
Doorknob, it should have been "is terrible".

Another case of the pot calling the kettle black.
Open mouth, change feet.

Regards,
David

On 2023-09-05 20:46, Bill Johnson wrote:
> I never once said it would assemble or run. I can see why you guys went into 
> IT. Your comprehension of basic English are terrible.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
>  wrote:
>
> Oh that's funny!  Then what are these notes from you I found in my trash
> folder?  Sounds like you were sure it would assemble and run perfectly,
> and also be able to take over someone's job today.
>
>    Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
>    of you assembler geniuses could test it.
>
>    Lol, how about going to chatgpt and asking the same question. So that
>    cut and paste isn’t a factor.
>
>    What are you afraid of? That a computer can do what you do? That your
>    “skills” aren’t all that impressive and can be automated away?
>
> On 9/5/2023 4:47 PM, Bill Johnson wrote:
>> I never presented it as a working model.
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-06 Thread Wayne Bickerdike

My favourite use of Assembler was an E15 sort exit. I developed it to
enable access to CA-Datacom database tables. It was originally written for
a VSE shop and it proved to be so useful (and fast), I maintained the code
when I worked in MVS shops. It was enhanced over the years to be condensed
down to a single macro with parameters to define the table name and
optional key. For those familiar with Datacom, there are two simple fast
retrieval commands, GETPS (get physical) and GETIT (get in key sequence).

My final version used a parameter that enabled a single exit to cover any
table required, the parameter defined LRECL, Key name, table name. I don't
think an exit like this could be developed in COBOL without jumping through
hoops to perform the parsing required.

A classic example of how to process large tables in batch.

On Wed, Sep 6, 2023 at 5:30 PM Bernd Oppolzer 
wrote:

> Thanks a lot,
>
> it would be always better to give even a very small ASSEMBLER program a
> test run
> instead of simply posting it to a public web site.
> I will fix this on Wikipedia as soon as I can.
>
> I'm not sure if ASSEMBLER should be used by humans :-) given this episode.
> In fact, it was used in the past (heavily), because in the 1950s and
> 1960s, it was the only language we had.
> And it is still used on Mainframes (some say: Mainframe Assembler is the
> only usable Assembler, all others are not)
> and as long as we have large code bases in Assembler, there is no other
> way than supporting it
> (and we have large code bases, this is what John Ehrman once told me ...
> most customers who still have that
> don't want to talk about it).
>
> Anyway: the reasons to learn it (like: to understand the code produced
> by other language translators better etc.
> and to understand language translators, BTW) are very valid, and that's
> what Ray Mullins (liebe Grüße)
> tells in his papers, too, if I understand him right.
>
> Another fun story:
>
> Once a co-worker of mine (at the large insurance company mentioned
> earlier) had a problem with IBM software,
> and while communicating with IBM, he posted a bit of ASSEMBLER code
> showing the error, and the answer of
> IBM support was "Customer should not use ASSEMBLER" :-)
>
> Kind regards
> Bernd
>
>
> Am 06.09.2023 um 05:44 schrieb Tom Brennan:
> > Your sample assembled fine but abended 0C1.  I made some minor mods.
> > Hope you don't mind my pretend German in the comments :)
> >
> > The biggest problem is trying to use R15 as a base.  That gets messed
> > up by OPEN.  The other problem is LA instead of L when loading R13 for
> > the return.  I mix those up a lot myself.
> >
> > https://www.mildredbrennan.com/mvs/hello.png
> >
> > P.S. My wife and I were in München last May.  Beautiful city and it
> > was fun trying to understand the language based on a high-school class.
> >
> >
> >
> > On 9/5/2023 6:19 PM, Bernd Oppolzer wrote:
> >> FWIW:
> >>
> >> ChatGPT could have used this ASSEMBLER program, which I posted some
> >> years ago
> >> to German Wikpedia ... this does not do the addition of two integers,
> >> but instead it
> >> is a simple Hello World program. In contrast to the program provided
> >> by ChatGPT,
> >> it has no errors (I hope) and it will work.
> >>
> >>
> https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER
> >>
> >>
> >> Kind regards
> >>
> >> Bernd
> >>
> >
> > --
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>


-- 
Wayne V. Bickerdike

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Thanks a lot,

it would be always better to give even a very small ASSEMBLER program a
test run

instead of simply posting it to a public web site.
I will fix this on Wikipedia as soon as I can.

I'm not sure if ASSEMBLER should be used by humans :-) given this episode.
In fact, it was used in the past (heavily), because in the 1950s and
1960s, it was the only language we had.
And it is still used on Mainframes (some say: Mainframe Assembler is the
only usable Assembler, all others are not)
and as long as we have large code bases in Assembler, there is no other
way than supporting it
(and we have large code bases, this is what John Ehrman once told me ...
most customers who still have that

don't want to talk about it).

Anyway: the reasons to learn it (like: to understand the code produced
by other language translators better etc.
and to understand language translators, BTW) are very valid, and that's
what Ray Mullins (liebe Grüße)

tells in his papers, too, if I understand him right.

Another fun story:

Once a co-worker of mine (at the large insurance company mentioned
earlier) had a problem with IBM software,
and while communicating with IBM, he posted a bit of ASSEMBLER code
showing the error, and the answer of

IBM support was "Customer should not use ASSEMBLER" :-)

Kind regards
Bernd

Am 06.09.2023 um 05:44 schrieb Tom Brennan:
Your sample assembled fine but abended 0C1. I made some minor mods.
Hope you don't mind my pretend German in the comments :)

The biggest problem is trying to use R15 as a base. That gets messed
up by OPEN. The other problem is LA instead of L when loading R13 for
the return. I mix those up a lot myself.

https://www.mildredbrennan.com/mvs/hello.png

P.S. My wife and I were in München last May. Beautiful city and it
was fun trying to understand the language based on a high-school class.

On 9/5/2023 6:19 PM, Bernd Oppolzer wrote:

FWIW:

ChatGPT could have used this ASSEMBLER program, which I posted some
years ago
to German Wikpedia ... this does not do the addition of two integers,
but instead it
is a simple Hello World program. In contrast to the program provided
by ChatGPT,

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER

Kind regards

Bernd

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Your sample assembled fine but abended 0C1.  I made some minor mods. 
Hope you don't mind my pretend German in the comments :)


The biggest problem is trying to use R15 as a base.  That gets messed up 
by OPEN.  The other problem is LA instead of L when loading R13 for the 
return.  I mix those up a lot myself.


https://www.mildredbrennan.com/mvs/hello.png

P.S. My wife and I were in München last May.  Beautiful city and it was 
fun trying to understand the language based on a high-school class.


On 9/5/2023 6:19 PM, Bernd Oppolzer wrote:

FWIW:

ChatGPT could have used this ASSEMBLER program, which I posted some 
years ago
to German Wikpedia ... this does not do the addition of two integers, 
but instead it
is a simple Hello World program. In contrast to the program provided by 
ChatGPT,

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER 



Kind regards

Bernd



--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Well, it depends.  My #ENTER allocates a large stack area for all parms 
and save areas used within the macro set (and associated programs). 
That way each subprogram doesn't have to do it's own getmain and 
chaining.  The plan was to be able to code ASM with some of the ease of 
C coding, especially around string processing which can be pretty 
difficult in ASM.


On 9/5/2023 7:27 PM, Paul Gilmartin wrote:

On Tue, 5 Sep 2023 19:03:53 -0700, Tom Brennan wrote:


Oops... Yes!  I was thinking ENTER/EXIT.  My own macro set uses #ENTER
and #EXIT.  I put the pound sign on everything so there's no confusion
with real instructions or IBM macros (well, at least I hope!)


At that, I'll switch to the Dark Side for a while.  If IBM's macros were good
enough programmers wouldn't be tempted to devise alternatives.

I've worked for a couple projects that did so.  One enhancement was to
extend the RSA so R13 could be used as a base for working storage,
a practice that others have harshly criticized as dangerous.  Another
was to preserve the CC through exit, which I disliked (didn't work on 370
because it used IPM, SPM.)



--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Tue, 5 Sep 2023 19:03:53 -0700, Tom Brennan wrote:

>Oops... Yes!  I was thinking ENTER/EXIT.  My own macro set uses #ENTER
>and #EXIT.  I put the pound sign on everything so there's no confusion
>with real instructions or IBM macros (well, at least I hope!)
>
At that, I'll switch to the Dark Side for a while.  If IBM's macros were good
enough programmers wouldn't be tempted to devise alternatives.

I've worked for a couple projects that did so.  One enhancement was to
extend the RSA so R13 could be used as a base for working storage,
a practice that others have harshly criticized as dangerous.  Another
was to preserve the CC through exit, which I disliked (didn't work on 370
because it used IPM, SPM.)

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

The "version history" of the German Wikipedia article shows that I added
this ASSEMBLER source code in 2015.
The page already existed, but there was no Mainframe example, which
motivated me to add one.
I thought some minutes about adding another source using the ASSEMBLER
of the German Telefunken TR 440 mainframe
of the 1970s (TAS = Telefunken Assembler Sprache), but I didn't succeed
so far. That was the machine which
impressed me most when I started my studies of computer science in 1977
at Stuttgart university.

https://www.gettyimages.de/detail/nachrichtenfoto/grossrechner-tr-440-von-telefunken-1970-nachrichtenfoto/542347199

The comments under the article which tell some facts about ASSEMBLER
source code layout (columns 10 and 16 etc.)

have been added later by another Wikipedia author and are partly wrong.

This conversation motivated me to correct the comments ... we'll see how
long it takes until my corrections are

verified by the Wikipedia people and online.

All in German ... sorry about that.

Kind regards

Bernd

Am 06.09.2023 um 03:35 schrieb Bernd Oppolzer:

Maybe the program disqualifies because of the German comments?
But: this should be no problem for ChatGPT ... translation to english ...

Kind regards

Bernd

Am 06.09.2023 um 03:31 schrieb Bernd Oppolzer:

What I meant to say:

it would have been better, if ChatGPT had used this (my) ASSEMBLER
program from German Wikipedia ...

but apparently, it found the bad program from another source ???
Bill did not ask for a certain logic in his request; he simply asked
for some mainframe Assembler program

(not specific). So my Hello World program would qualify, too.

It would be interesting to know how ChatGPT determines which sources
are more reliable than others ...

Kind regards

Bernd

Am 06.09.2023 um 03:19 schrieb Bernd Oppolzer:

FWIW:

ChatGPT could have used this ASSEMBLER program, which I posted some
years ago
to German Wikpedia ... this does not do the addition of two
integers, but instead it
is a simple Hello World program. In contrast to the program provided
by ChatGPT,

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER

Kind regards

Bernd

Am 06.09.2023 um 01:47 schrieb Bill Johnson:

I never presented it as a working model.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer
wrote:

I am not bashing it. I am simply telling you that it has a bunch of
errors and it will not work.

It's kind of interesting to me that, while I try to answer repectfully
to your mails,
almost every answer from you contains the word "idiot" or "idiotic",
which is the same in German, so I understand that well.
Is that a specific way to support your arguments?

Am 06.09.2023 um 01:31 schrieb Bill Johnson:
I find it stunning the technology people are trying to hang onto
the past (assembler) and bashing the future. (ChatGPT) Or perhaps
that’s what aging people do.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Oops... Yes!  I was thinking ENTER/EXIT.  My own macro set uses #ENTER 
and #EXIT.  I put the pound sign on everything so there's no confusion 
with real instructions or IBM macros (well, at least I hope!)


On 9/5/2023 6:52 PM, Paul Gilmartin wrote:

On Tue, 5 Sep 2023 11:27:15 -0700, Tom Brennan wrote:


Which is a bit strange, because I would expect that every ASM program
ChatGPT looked at would have had something for that at the top and
bottom, even if it was just ENTRY/EXIT macros or similar.


Isn't ENTRY an Assembler instruction, not a macro?



--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


True, but you certainly implied it in the notes I pasted below.

And yes, my comprehension of basic English are terrible.  My biggest 
problem is with singular and plural verbs.


On 9/5/2023 5:46 PM, Bill Johnson wrote:

I never once said it would assemble or run. I can see why you guys went into 
IT. Your comprehension of basic English are terrible.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
 wrote:

Oh that's funny!  Then what are these notes from you I found in my trash
folder?  Sounds like you were sure it would assemble and run perfectly,
and also be able to take over someone's job today.

   Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
   of you assembler geniuses could test it.

   Lol, how about going to chatgpt and asking the same question. So that
   cut and paste isn’t a factor.

   What are you afraid of? That a computer can do what you do? That your
   “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:

I never presented it as a working model.


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Tue, 5 Sep 2023 11:27:15 -0700, Tom Brennan wrote:

>Which is a bit strange, because I would expect that every ASM program
>ChatGPT looked at would have had something for that at the top and
>bottom, even if it was just ENTRY/EXIT macros or similar.
> 
Isn't ENTRY an Assembler instruction, not a macro?

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Maybe the program disqualifies because of the German comments?
But: this should be no problem for ChatGPT ... translation to english ...

Kind regards

Bernd

Am 06.09.2023 um 03:31 schrieb Bernd Oppolzer:

What I meant to say:

it would have been better, if ChatGPT had used this (my) ASSEMBLER
program from German Wikipedia ...

but apparently, it found the bad program from another source ???
Bill did not ask for a certain logic in his request; he simply asked
for some mainframe Assembler program

(not specific). So my Hello World program would qualify, too.

It would be interesting to know how ChatGPT determines which sources
are more reliable than others ...

Kind regards

Bernd

Am 06.09.2023 um 03:19 schrieb Bernd Oppolzer:

FWIW:

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER

Kind regards

Bernd

Am 06.09.2023 um 01:47 schrieb Bill Johnson:

I never presented it as a working model.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer
wrote:

I am not bashing it. I am simply telling you that it has a bunch of
errors and it will not work.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

What I meant to say:

it would have been better, if ChatGPT had used this (my) ASSEMBLER
program from German Wikipedia ...

but apparently, it found the bad program from another source ???
Bill did not ask for a certain logic in his request; he simply asked for
some mainframe Assembler program

(not specific). So my Hello World program would qualify, too.

It would be interesting to know how ChatGPT determines which sources are
more reliable than others ...

Kind regards

Bernd

Am 06.09.2023 um 03:19 schrieb Bernd Oppolzer:

FWIW:

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER

Kind regards

Bernd

Am 06.09.2023 um 01:47 schrieb Bill Johnson:

I never presented it as a working model.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer
wrote:

I am not bashing it. I am simply telling you that it has a bunch of
errors and it will not work.

Am 06.09.2023 um 01:31 schrieb Bill Johnson:
I find it stunning the technology people are trying to hang onto the
past (assembler) and bashing the future. (ChatGPT) Or perhaps that’s
what aging people do.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

FWIW:

it has no errors (I hope) and it will work.

https://de.wikipedia.org/wiki/Liste_von_Hallo-Welt-Programmen/Assembler#IBM-Mainframe-ASSEMBLER

Kind regards

Bernd

Am 06.09.2023 um 01:47 schrieb Bill Johnson:

I never presented it as a working model.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer
wrote:

I am not bashing it. I am simply telling you that it has a bunch of
errors and it will not work.

Am 06.09.2023 um 01:31 schrieb Bill Johnson:

I find it stunning the technology people are trying to hang onto the past
(assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging
people do.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Hi Bill,
You said: "...Your comprehension of basic English are terrible. ..."
Doorknob, it should have been "is terrible".

Another case of the pot calling the kettle black.
Open mouth, change feet.

Regards,
David

On 2023-09-05 20:46, Bill Johnson wrote:

I never once said it would assemble or run. I can see why you guys went into 
IT. Your comprehension of basic English are terrible.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
 wrote:

Oh that's funny!  Then what are these notes from you I found in my trash
folder?  Sounds like you were sure it would assemble and run perfectly,
and also be able to take over someone's job today.

   Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
   of you assembler geniuses could test it.

   Lol, how about going to chatgpt and asking the same question. So that
   cut and paste isn’t a factor.

   What are you afraid of? That a computer can do what you do? That your
   “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:

I never presented it as a working model.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I never once said it would assemble or run. I can see why you guys went into 
IT. Your comprehension of basic English are terrible.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 8:22 PM, Tom Brennan 
 wrote:

Oh that's funny!  Then what are these notes from you I found in my trash 
folder?  Sounds like you were sure it would assemble and run perfectly, 
and also be able to take over someone's job today.

  Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
  of you assembler geniuses could test it.

  Lol, how about going to chatgpt and asking the same question. So that
  cut and paste isn’t a factor.

  What are you afraid of? That a computer can do what you do? That your
  “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:
> I never presented it as a working model.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Here’s a prime example Bernd. Dummy Dave always likes his superior cut downs. 
Thinks he’s intelligent.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 8:39 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Tom,
+1
You forget that it took Bill and 2 colleagues to modify IEFUSI.

Regards,
David

On 2023-09-05 20:21, Tom Brennan wrote:
> Oh that's funny!  Then what are these notes from you I found in my 
> trash folder?  Sounds like you were sure it would assemble and run 
> perfectly, and also be able to take over someone's job today.
>
>   Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
>   of you assembler geniuses could test it.
>
>   Lol, how about going to chatgpt and asking the same question. So that
>   cut and paste isn’t a factor.
>
>   What are you afraid of? That a computer can do what you do? That your
>   “skills” aren’t all that impressive and can be automated away?
>
> On 9/5/2023 4:47 PM, Bill Johnson wrote:
>> I never presented it as a working model.
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

As always happens here. I am attacked and disrespected. Then when I respond in 
kind, your cult feigns innocence. 

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 8:19 PM, Bernd Oppolzer 
 wrote:

I told you "I try to answer respectfully" ...
doesn't work always, especially if I am called an idiot in the very same 
mail that I am answering to.

Kind regards

Bernd

Am 06.09.2023 um 01:53 schrieb Bill Johnson:
> If you consider this respectful, there’s something wrong with you.
>
> “So your JCL expertise qualifies you as a systems programmer ... that's
> interesting.”
>
>
> Sent from Yahoo Mail for iPhone
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Hi Tom,
+1
You forget that it took Bill and 2 colleagues to modify IEFUSI.

Regards,
David

On 2023-09-05 20:21, Tom Brennan wrote:
Oh that's funny!  Then what are these notes from you I found in my 
trash folder?  Sounds like you were sure it would assemble and run 
perfectly, and also be able to take over someone's job today.


  Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
  of you assembler geniuses could test it.

  Lol, how about going to chatgpt and asking the same question. So that
  cut and paste isn’t a factor.

  What are you afraid of? That a computer can do what you do? That your
  “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:

I never presented it as a working model.


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Oh that's funny!  Then what are these notes from you I found in my trash 
folder?  Sounds like you were sure it would assemble and run perfectly, 
and also be able to take over someone's job today.


  Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
  of you assembler geniuses could test it.

  Lol, how about going to chatgpt and asking the same question. So that
  cut and paste isn’t a factor.

  What are you afraid of? That a computer can do what you do? That your
  “skills” aren’t all that impressive and can be automated away?

On 9/5/2023 4:47 PM, Bill Johnson wrote:

I never presented it as a working model.


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


I told you "I try to answer respectfully" ...
doesn't work always, especially if I am called an idiot in the very same 
mail that I am answering to.


Kind regards

Bernd


Am 06.09.2023 um 01:53 schrieb Bill Johnson:

If you consider this respectful, there’s something wrong with you.

“So your JCL expertise qualifies you as a systems programmer ... that's
interesting.”


Sent from Yahoo Mail for iPhone



--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

If you consider this respectful, there’s something wrong with you. 

“So your JCL expertise qualifies you as a systems programmer ... that's 
interesting.”

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer 
 wrote:

I am not bashing it. I am simply telling you that it has a bunch of 
errors and it will not work.

It's kind of interesting to me that, while I try to answer repectfully 
to your mails,
almost every answer from you contains the word "idiot" or "idiotic",
which is the same in German, so I understand that well.
Is that a specific way to support your arguments?

Am 06.09.2023 um 01:31 schrieb Bill Johnson:
> I find it stunning the technology people are trying to hang onto the past 
> (assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging 
> people do.
>
>
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

No, but someone who extrapolates my JCL expertise as my only expertise deserves 
that response. Or perhaps dummkopf. Yes, I have 3 years of German, which served 
me well in Munich, Regensburg, Austria, & Switzerland. 

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer 
 wrote:

I am not bashing it. I am simply telling you that it has a bunch of 
errors and it will not work.

It's kind of interesting to me that, while I try to answer repectfully 
to your mails,
almost every answer from you contains the word "idiot" or "idiotic",
which is the same in German, so I understand that well.
Is that a specific way to support your arguments?

Am 06.09.2023 um 01:31 schrieb Bill Johnson:
> I find it stunning the technology people are trying to hang onto the past 
> (assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging 
> people do.
>
>
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I never presented it as a working model.

Sent from Yahoo Mail for iPhone

On Tuesday, September 5, 2023, 7:36 PM, Bernd Oppolzer 
 wrote:

I am not bashing it. I am simply telling you that it has a bunch of 
errors and it will not work.

It's kind of interesting to me that, while I try to answer repectfully 
to your mails,
almost every answer from you contains the word "idiot" or "idiotic",
which is the same in German, so I understand that well.
Is that a specific way to support your arguments?

Am 06.09.2023 um 01:31 schrieb Bill Johnson:
> I find it stunning the technology people are trying to hang onto the past 
> (assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging 
> people do.
>
>
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Joe Monk

It will abend for sure.

Joe



On Tue, Sep 5, 2023 at 5:52 PM Bernd Oppolzer 
wrote:

> It will not work, because almost every single instruction has an error
> or two.
> Every programmer with a little bit ASSMBLER experience can see this;
> this ChatGPT program has no grasp of instruction formats, DCBs or the
> proper
> use of I/O macros. I will not go into the details here ... the ASSEMBLER
> people know
> what I'm talking about, and the others are not interested.
>
> Kind regards
>
> Bernd
>
>
> Am 05.09.2023 um 18:00 schrieb Bill Johnson:
> > Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
> of you assembler geniuses could test it.
> >
> > Like Mullins said, and others mentioned, most companies that run z/OS
> don’t need assembler programmers. That numbers in the thousands if not ten
> thousand. Whereas ISV’s who are the likely users of Assembler programming,
> number in the hundreds, maybe. So install on Systems Programmers.
> >
> >
> > Sent from Yahoo Mail for iPhone
> >
> >
> > On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson 
> wrote:
> >
> > I doubt it will assemble. And even if it does, the results are
> > unpredictable, other than it will probably ABEND for one reason
> > or another.
> >
> > There are no DCB, OPEN, CLOSE macros while GET and PUT are being
> > used.
> >
> > Me thinks this AI system is confusing a few different assembly
> > languages together. I wonder how close they came for DOS I/O.
> > Steve Thompson
> >
> >
> >
> > On 9/5/2023 11:20 AM, Tom Marchant wrote:
> >> You're right, Tom. That is not a program. Certainly not one that will
> do what it claims to do.
> >>
> >> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
> >>  wrote:
> >>> I can't be sure I formatted it properly, but after looking over the
> >>> code, I have nothing to say but WTF? 
> >>>
> >>>PRINT NOGEN
> >>>TITLE 'Simple Addition Program'
> >>> ** Define storage for input numbers and result
> >>> *
> >>> NUM1DSFFirst input number
> >>> NUM2DSFSecond input number
> >>> RESULT  DSFResult of addition
> >>> ** Main program
> >>> *
> >>> MAINC  0NUM1  Check if NUM1 is zero
> >>>BEZEROBranch to ZERO if true
> >>> ** Read the first number from input
> >>> *
> >>>GETNUM1,NUMIN  Read NUM1 from input
> >>>LA0,NUM1  Load NUM1 into register
> >>> ** Read the second number from input
> >>> *
> >>>GETNUM2,NUMIN  Read NUM2 from input
> >>>A  NUM1,NUM2  Add NUM1 and NUM2
> >>>STNUM1,RESULTStore the result in RESULT
> >>> ** Print the result
> >>> *
> >>>PUTRESULT,NUMOUT  Print the result
> >>> ** Terminate the program
> >>> *
> >>>SR15,15  Set return code to 0
> >>>BR14  Return to caller
> >>> ** Define input and output areas
> >>> *
> >>> NUMINDCF'0'  Input buffer for numbers
> >>> NUMOUT  DCF'0'  Output buffer for result
> >>> ZERODCF'0'  Constant zero
> >>>END  MAINEnd of program
> >> --
> >> For IBM-MAIN subscribe / signoff / archive access instructions,
> >> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
> > --
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
> >
> >
> >
> >
> > --
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I am not bashing it. I am simply telling you that it has a bunch of 
errors and it will not work.


It's kind of interesting to me that, while I try to answer repectfully 
to your mails,

almost every answer from you contains the word "idiot" or "idiotic",
which is the same in German, so I understand that well.
Is that a specific way to support your arguments?


Am 06.09.2023 um 01:31 schrieb Bill Johnson:

I find it stunning the technology people are trying to hang onto the past 
(assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging 
people do.





--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I find it stunning the technology people are trying to hang onto the past 
(assembler) and bashing the future. (ChatGPT) Or perhaps that’s what aging 
people do.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 7:04 PM, Bill Johnson 
<0047540adefe-dmarc-requ...@listserv.ua.edu> wrote:

You people are idiots. Chatgpt just came out. Nobody, including me, said it was 
going to replace you today, or tomorrow. But, it will replace you.

Autonomous vehicles are coming too. In fact, they are already on the road. 
Perfect? Not yet. But getting closer daily.

Flying cars are a few decades away. Although flying taxis are closer than you 
think. 

https://www.npr.org/2023/07/01/1185060325/joby-electric-flying-taxi




Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 6:52 PM, Bernd Oppolzer 
 wrote:

It will not work, because almost every single instruction has an error 
or two.
Every programmer with a little bit ASSMBLER experience can see this;
this ChatGPT program has no grasp of instruction formats, DCBs or the 
proper
use of I/O macros. I will not go into the details here ... the ASSEMBLER 
people know
what I'm talking about, and the others are not interested.

Kind regards

Bernd


Am 05.09.2023 um 18:00 schrieb Bill Johnson:
> Why do you doubt it? Is it because you hope it doesn’t? Certainly, one of you 
> assembler geniuses could test it.
>
> Like Mullins said, and others mentioned, most companies that run z/OS don’t 
> need assembler programmers. That numbers in the thousands if not ten 
> thousand. Whereas ISV’s who are the likely users of Assembler programming, 
> number in the hundreds, maybe. So install on Systems Programmers.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson  
> wrote:
>
> I doubt it will assemble. And even if it does, the results are
> unpredictable, other than it will probably ABEND for one reason
> or another.
>
> There are no DCB, OPEN, CLOSE macros while GET and PUT are being
> used.
>
> Me thinks this AI system is confusing a few different assembly
> languages together. I wonder how close they came for DOS I/O.
> Steve Thompson
>
>
>
> On 9/5/2023 11:20 AM, Tom Marchant wrote:
>> You're right, Tom. That is not a program. Certainly not one that will do 
>> what it claims to do.
>>
>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
>>  wrote:
>>> I can't be sure I formatted it properly, but after looking over the
>>> code, I have nothing to say but WTF? 
>>>
>>>            PRINT NOGEN
>>>            TITLE 'Simple Addition Program'
>>> ** Define storage for input numbers and result
>>> *
>>> NUM1    DS    F            First input number
>>> NUM2    DS    F            Second input number
>>> RESULT  DS    F            Result of addition
>>> ** Main program
>>> *
>>> MAIN    C      0        NUM1  Check if NUM1 is zero
>>>            BE    ZERO            Branch to ZERO if true
>>> ** Read the first number from input
>>> *
>>>            GET    NUM1,NUMIN      Read NUM1 from input
>>>            LA    0,NUM1          Load NUM1 into register
>>> ** Read the second number from input
>>> *
>>>            GET    NUM2,NUMIN      Read NUM2 from input
>>>            A      NUM1,NUM2      Add NUM1 and NUM2
>>>            ST    NUM1,RESULT    Store the result in RESULT
>>> ** Print the result
>>> *
>>>            PUT    RESULT,NUMOUT  Print the result
>>> ** Terminate the program
>>> *
>>>            SR    15,15          Set return code to 0
>>>            BR    14              Return to caller
>>> ** Define input and output areas
>>> *
>>> NUMIN    DC    F'0'          Input buffer for numbers
>>> NUMOUT  DC    F'0'          Output buffer for result
>>> ZERO    DC    F'0'          Constant zero
>>>            END  MAIN            End of program
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Joe Monk

It doesn't even establish addressability.

Joe

On Tue, Sep 5, 2023 at 5:52 PM Bernd Oppolzer 
wrote:

> It will not work, because almost every single instruction has an error
> or two.
> Every programmer with a little bit ASSMBLER experience can see this;
> this ChatGPT program has no grasp of instruction formats, DCBs or the
> proper
> use of I/O macros. I will not go into the details here ... the ASSEMBLER
> people know
> what I'm talking about, and the others are not interested.
>
> Kind regards
>
> Bernd
>
>
> Am 05.09.2023 um 18:00 schrieb Bill Johnson:
> > Why do you doubt it? Is it because you hope it doesn’t? Certainly, one
> of you assembler geniuses could test it.
> >
> > Like Mullins said, and others mentioned, most companies that run z/OS
> don’t need assembler programmers. That numbers in the thousands if not ten
> thousand. Whereas ISV’s who are the likely users of Assembler programming,
> number in the hundreds, maybe. So install on Systems Programmers.
> >
> >
> > Sent from Yahoo Mail for iPhone
> >
> >
> > On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson 
> wrote:
> >
> > I doubt it will assemble. And even if it does, the results are
> > unpredictable, other than it will probably ABEND for one reason
> > or another.
> >
> > There are no DCB, OPEN, CLOSE macros while GET and PUT are being
> > used.
> >
> > Me thinks this AI system is confusing a few different assembly
> > languages together. I wonder how close they came for DOS I/O.
> > Steve Thompson
> >
> >
> >
> > On 9/5/2023 11:20 AM, Tom Marchant wrote:
> >> You're right, Tom. That is not a program. Certainly not one that will
> do what it claims to do.
> >>
> >> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
> >>  wrote:
> >>> I can't be sure I formatted it properly, but after looking over the
> >>> code, I have nothing to say but WTF? 
> >>>
> >>>PRINT NOGEN
> >>>TITLE 'Simple Addition Program'
> >>> ** Define storage for input numbers and result
> >>> *
> >>> NUM1DSFFirst input number
> >>> NUM2DSFSecond input number
> >>> RESULT  DSFResult of addition
> >>> ** Main program
> >>> *
> >>> MAINC  0NUM1  Check if NUM1 is zero
> >>>BEZEROBranch to ZERO if true
> >>> ** Read the first number from input
> >>> *
> >>>GETNUM1,NUMIN  Read NUM1 from input
> >>>LA0,NUM1  Load NUM1 into register
> >>> ** Read the second number from input
> >>> *
> >>>GETNUM2,NUMIN  Read NUM2 from input
> >>>A  NUM1,NUM2  Add NUM1 and NUM2
> >>>STNUM1,RESULTStore the result in RESULT
> >>> ** Print the result
> >>> *
> >>>PUTRESULT,NUMOUT  Print the result
> >>> ** Terminate the program
> >>> *
> >>>SR15,15  Set return code to 0
> >>>BR14  Return to caller
> >>> ** Define input and output areas
> >>> *
> >>> NUMINDCF'0'  Input buffer for numbers
> >>> NUMOUT  DCF'0'  Output buffer for result
> >>> ZERODCF'0'  Constant zero
> >>>END  MAINEnd of program
> >> --
> >> For IBM-MAIN subscribe / signoff / archive access instructions,
> >> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
> > --
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
> >
> >
> >
> >
> > --
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

You people are idiots. Chatgpt just came out. Nobody, including me, said it was 
going to replace you today, or tomorrow. But, it will replace you.

Autonomous vehicles are coming too. In fact, they are already on the road. 
Perfect? Not yet. But getting closer daily.

Flying cars are a few decades away. Although flying taxis are closer than you 
think. 

https://www.npr.org/2023/07/01/1185060325/joby-electric-flying-taxi




Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 6:52 PM, Bernd Oppolzer 
 wrote:

It will not work, because almost every single instruction has an error 
or two.
Every programmer with a little bit ASSMBLER experience can see this;
this ChatGPT program has no grasp of instruction formats, DCBs or the 
proper
use of I/O macros. I will not go into the details here ... the ASSEMBLER 
people know
what I'm talking about, and the others are not interested.

Kind regards

Bernd


Am 05.09.2023 um 18:00 schrieb Bill Johnson:
> Why do you doubt it? Is it because you hope it doesn’t? Certainly, one of you 
> assembler geniuses could test it.
>
> Like Mullins said, and others mentioned, most companies that run z/OS don’t 
> need assembler programmers. That numbers in the thousands if not ten 
> thousand. Whereas ISV’s who are the likely users of Assembler programming, 
> number in the hundreds, maybe. So install on Systems Programmers.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson  
> wrote:
>
> I doubt it will assemble. And even if it does, the results are
> unpredictable, other than it will probably ABEND for one reason
> or another.
>
> There are no DCB, OPEN, CLOSE macros while GET and PUT are being
> used.
>
> Me thinks this AI system is confusing a few different assembly
> languages together. I wonder how close they came for DOS I/O.
> Steve Thompson
>
>
>
> On 9/5/2023 11:20 AM, Tom Marchant wrote:
>> You're right, Tom. That is not a program. Certainly not one that will do 
>> what it claims to do.
>>
>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
>>  wrote:
>>> I can't be sure I formatted it properly, but after looking over the
>>> code, I have nothing to say but WTF? 
>>>
>>>            PRINT NOGEN
>>>            TITLE 'Simple Addition Program'
>>> ** Define storage for input numbers and result
>>> *
>>> NUM1    DS    F            First input number
>>> NUM2    DS    F            Second input number
>>> RESULT  DS    F            Result of addition
>>> ** Main program
>>> *
>>> MAIN    C      0        NUM1  Check if NUM1 is zero
>>>            BE    ZERO            Branch to ZERO if true
>>> ** Read the first number from input
>>> *
>>>            GET    NUM1,NUMIN      Read NUM1 from input
>>>            LA    0,NUM1          Load NUM1 into register
>>> ** Read the second number from input
>>> *
>>>            GET    NUM2,NUMIN      Read NUM2 from input
>>>            A      NUM1,NUM2      Add NUM1 and NUM2
>>>            ST    NUM1,RESULT    Store the result in RESULT
>>> ** Print the result
>>> *
>>>            PUT    RESULT,NUMOUT  Print the result
>>> ** Terminate the program
>>> *
>>>            SR    15,15          Set return code to 0
>>>            BR    14              Return to caller
>>> ** Define input and output areas
>>> *
>>> NUMIN    DC    F'0'          Input buffer for numbers
>>> NUMOUT  DC    F'0'          Output buffer for result
>>> ZERO    DC    F'0'          Constant zero
>>>            END  MAIN            End of program
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

It will not work, because almost every single instruction has an error 
or two.

Every programmer with a little bit ASSMBLER experience can see this;
this ChatGPT program has no grasp of instruction formats, DCBs or the 
proper
use of I/O macros. I will not go into the details here ... the ASSEMBLER 
people know

what I'm talking about, and the others are not interested.

Kind regards

Bernd


Am 05.09.2023 um 18:00 schrieb Bill Johnson:

Why do you doubt it? Is it because you hope it doesn’t? Certainly, one of you 
assembler geniuses could test it.

Like Mullins said, and others mentioned, most companies that run z/OS don’t 
need assembler programmers. That numbers in the thousands if not ten thousand. 
Whereas ISV’s who are the likely users of Assembler programming, number in the 
hundreds, maybe. So install on Systems Programmers.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson  wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one reason
or another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being
used.

Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:

You're right, Tom. That is not a program. Certainly not one that will do what 
it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

           PRINT NOGEN
           TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1    DS    F            First input number
NUM2    DS    F            Second input number
RESULT  DS    F            Result of addition
** Main program
*
MAIN    C      0        NUM1  Check if NUM1 is zero
           BE    ZERO            Branch to ZERO if true
** Read the first number from input
*
           GET    NUM1,NUMIN      Read NUM1 from input
           LA    0,NUM1          Load NUM1 into register
** Read the second number from input
*
           GET    NUM2,NUMIN      Read NUM2 from input
           A      NUM1,NUM2      Add NUM1 and NUM2
           ST    NUM1,RESULT    Store the result in RESULT
** Print the result
*
           PUT    RESULT,NUMOUT  Print the result
** Terminate the program
*
           SR    15,15          Set return code to 0
           BR    14              Return to caller
** Define input and output areas
*
NUMIN    DC    F'0'          Input buffer for numbers
NUMOUT  DC    F'0'          Output buffer for result
ZERO    DC    F'0'          Constant zero
           END  MAIN            End of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Legal Problems with ChatGPT [Was Re: Simple request from chatGPT to write assembler program.]

Here is a take-off on the forbes article which is from the Legal 
Ethics Law 360 email list (I also get the transportation law 
stuff too):



Insurance Coverage For ChatGPT Legal Fiasco: A Hypothetical 



William Passannante at Anderson Kill draws on the recent case of 
an attorney sanctioned by the Southern District of New York for 
submitting a ChatGPT-authored brief to discuss what the insurance 
coverage for the attorney's hypothetical claim might look like.



And I think this is the original case:


Attys Behind ChatGPT Fiasco Apologize To Client, 7 Judges 



By Hailey Konnath

A pair of New York personal injury attorneys apologized Wednesday 
to seven federal and state judges and to a client for submitting 
a brief prepared by artificial intelligence that cited 
nonexistent case law attributed to the judges, according to 
copies of the letters filed in Manhattan federal court.


And there are now other articles over whether or not chatGPT can 
defame a person or something like that... And something about the 
case being remanded.. (my head hurts).



Steve Thompson



On 9/5/2023 5:11 PM, Mike Schwab wrote:

https://www.forbes.com/sites/mollybohannon/2023/06/08/lawyer-used-chatgpt-in-court-and-cited-fake-cases-a-judge-is-considering-sanctions/

On Tue, Sep 5, 2023 at 4:03 PM Bob Bridges  wrote:

Can't remember whether I read about it here or somewhere else, but apparently 
there was a recent episode in which a lawyer got an AI machine to write a legal 
brief for him.  It looked impressive, but it turned out the precedents the 
brief cited didn't exist; the AI made them up.  The judge fined the lawyer.

---
Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313

/* The most important fundamental laws and facts of physical science have all 
been discovered, and these are now so firmly established that the possibility 
of their ever being supplemented in consequence of new discoveries is 
exceedingly remote.  -Abraham Albert Michelson in 1903 */

-Original Message-
From: IBM Mainframe Discussion List  On Behalf Of 
Dean Kent
Sent: Tuesday, September 5, 2023 12:46

I spent a bit of time playing with chatGPT to see what it could do.   So did my 
two sons - one an MS in biotech, the other a PhD in theoretical physics.We 
all came to the same conclusion - chatGPT is a very, very good Google search 
that can filter many different possible 'answers' and come to one that is 'most 
likely' based on various factors.  It has little to no creativity or 
understanding of what it is asked to do. Not surprising, but different than 
what the popular press seems to say about it.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN





--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Mike Schwab

https://www.forbes.com/sites/mollybohannon/2023/06/08/lawyer-used-chatgpt-in-court-and-cited-fake-cases-a-judge-is-considering-sanctions/

On Tue, Sep 5, 2023 at 4:03 PM Bob Bridges  wrote:
>
> Can't remember whether I read about it here or somewhere else, but apparently 
> there was a recent episode in which a lawyer got an AI machine to write a 
> legal brief for him.  It looked impressive, but it turned out the precedents 
> the brief cited didn't exist; the AI made them up.  The judge fined the 
> lawyer.
>
> ---
> Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313
>
> /* The most important fundamental laws and facts of physical science have all 
> been discovered, and these are now so firmly established that the possibility 
> of their ever being supplemented in consequence of new discoveries is 
> exceedingly remote.  -Abraham Albert Michelson in 1903 */
>
> -Original Message-
> From: IBM Mainframe Discussion List  On Behalf Of 
> Dean Kent
> Sent: Tuesday, September 5, 2023 12:46
>
> I spent a bit of time playing with chatGPT to see what it could do.   So did 
> my two sons - one an MS in biotech, the other a PhD in theoretical physics.   
>  We all came to the same conclusion - chatGPT is a very, very good Google 
> search that can filter many different possible 'answers' and come to one that 
> is 'most likely' based on various factors.  It has little to no creativity or 
> understanding of what it is asked to do. Not surprising, but different than 
> what the popular press seems to say about it.
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN



-- 
Mike A Schwab, Springfield IL USA
Where do Forest Rangers go to get away from it all?

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Nutz, I gave away that the code might assemble and run under 
VSE Oh the horrors of it all!!


Does this mean that Person of Interest is really true?

;-)

Steve Thompson


On 9/5/2023 4:45 PM, Tom Brennan wrote:
Quiet!! ChatGPT does this on purpose so it can read responses 
and get ASM training from us puny humans :)


On 9/5/2023 1:06 PM, Tom Marchant wrote:

Nor does it know how to code instructions.

I don't know what this should be, but it isn't adequateor 
correct:

MAIN C  0    NUM1   Check if NUM1 is zero


ZERO is not a label on code:

  BE ZERO    Branch to ZERO if true


NUM1 is not a DCB address

  GET    NUM1,NUMIN  Read NUM1 from input


Wrong:

  LA 0,NUM1  Load NUM1 into register


NUM2 is not a DCB address:

 GET    NUM2,NUMIN  Read NUM2 from input


NUM1 is not a register number:

  A  NUM1,NUM2   Add NUM1 and NUM2
  ST NUM1,RESULT Store the result in RESULT


RESULT is not a DCB address:

  PUT    RESULT,NUMOUT   Print the result




-- 


For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO 
IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Bob Bridges

Can't remember whether I read about it here or somewhere else, but apparently 
there was a recent episode in which a lawyer got an AI machine to write a legal 
brief for him.  It looked impressive, but it turned out the precedents the 
brief cited didn't exist; the AI made them up.  The judge fined the lawyer.

---
Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313

/* The most important fundamental laws and facts of physical science have all 
been discovered, and these are now so firmly established that the possibility 
of their ever being supplemented in consequence of new discoveries is 
exceedingly remote.  -Abraham Albert Michelson in 1903 */

-Original Message-
From: IBM Mainframe Discussion List  On Behalf Of 
Dean Kent
Sent: Tuesday, September 5, 2023 12:46

I spent a bit of time playing with chatGPT to see what it could do.   So did my 
two sons - one an MS in biotech, the other a PhD in theoretical physics.We 
all came to the same conclusion - chatGPT is a very, very good Google search 
that can filter many different possible 'answers' and come to one that is 'most 
likely' based on various factors.  It has little to no creativity or 
understanding of what it is asked to do. Not surprising, but different than 
what the popular press seems to say about it.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Quiet!!  ChatGPT does this on purpose so it can read responses and get 
ASM training from us puny humans :)


On 9/5/2023 1:06 PM, Tom Marchant wrote:

Nor does it know how to code instructions.

I don't know what this should be, but it isn't adequateor correct:

MAIN C  0NUM1   Check if NUM1 is zero


ZERO is not a label on code:

  BE ZEROBranch to ZERO if true


NUM1 is not a DCB address

  GETNUM1,NUMIN  Read NUM1 from input


Wrong:

  LA 0,NUM1  Load NUM1 into register


NUM2 is not a DCB address:

 GETNUM2,NUMIN  Read NUM2 from input


NUM1 is not a register number:

  A  NUM1,NUM2   Add NUM1 and NUM2
  ST NUM1,RESULT Store the result in RESULT


RESULT is not a DCB address:

  PUTRESULT,NUMOUT   Print the result




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Wayne Bickerdike

ChatGPT could have written the requirement in PL/I, compiled and produced
the Assembler listing. The Assembler generated would work, albeit
incredibly wordy.

It does appear that the PUT macro was confused usage of a PL/I PUT
statement.

No conversion attempted to get from full word to a displayable format (CVD,
UNPK).



On Wed, Sep 6, 2023 at 6:06 AM Tom Marchant <
000a2a8c2020-dmarc-requ...@listserv.ua.edu> wrote:

> Nor does it know how to code instructions.
>
> I don't know what this should be, but it isn't adequateor correct:
> >MAIN C  0NUM1   Check if NUM1 is zero
>
> ZERO is not a label on code:
> >  BE ZEROBranch to ZERO if true
>
> NUM1 is not a DCB address
> >  GETNUM1,NUMIN  Read NUM1 from input
>
> Wrong:
> >  LA 0,NUM1  Load NUM1 into register
>
> NUM2 is not a DCB address:
> > GETNUM2,NUMIN  Read NUM2 from input
>
> NUM1 is not a register number:
> >  A  NUM1,NUM2   Add NUM1 and NUM2
> >  ST NUM1,RESULT Store the result in RESULT
>
> RESULT is not a DCB address:
> >  PUTRESULT,NUMOUT   Print the result
>
> --
> Tom Marchant
>
> On Tue, 5 Sep 2023 14:10:20 -0400, David Spiegel 
> wrote:
>
> >Hi Tom,
> >It looks like ChatGPT is not aware of "Housekeeping".
> >
> >Regards,
> >David
> >
> >On 2023-09-05 13:47, Tom Brennan wrote:
> >> GET and PUT use R14, so as Tom Marchant said, if the program managed
> >> to get that far it would never return to the OS.
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>


-- 
Wayne V. Bickerdike

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Nor does it know how to code instructions.

I don't know what this should be, but it isn't adequateor correct:
>MAIN C  0NUM1   Check if NUM1 is zero

ZERO is not a label on code:
>  BE ZEROBranch to ZERO if true

NUM1 is not a DCB address
>  GETNUM1,NUMIN  Read NUM1 from input

Wrong:
>  LA 0,NUM1  Load NUM1 into register

NUM2 is not a DCB address:
> GETNUM2,NUMIN  Read NUM2 from input

NUM1 is not a register number:
>  A  NUM1,NUM2   Add NUM1 and NUM2
>  ST NUM1,RESULT Store the result in RESULT

RESULT is not a DCB address:
>  PUTRESULT,NUMOUT   Print the result

-- 
Tom Marchant

On Tue, 5 Sep 2023 14:10:20 -0400, David Spiegel  
wrote:

>Hi Tom,
>It looks like ChatGPT is not aware of "Housekeeping".
>
>Regards,
>David
>
>On 2023-09-05 13:47, Tom Brennan wrote:
>> GET and PUT use R14, so as Tom Marchant said, if the program managed
>> to get that far it would never return to the OS.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

And so we can now understand that when a paralegal or newly 
minted attorney uses it to find case law for points and 
authorities, it will will make them up to match what was being 
searched for when it prepares a motion it was asked for using the 
results of the search.


And some attorneys got a judge quite angry with them when they 
didn't tell the court this, but the opposing council pointed out 
they could not find any such case listed in the pleadings/motion. 
Then the judge's people also could not find same This is the 
kind of thing that concerns me about AI today. Once it has been 
taught enough to learn on its own


Steve Thompson

On 9/5/2023 12:46 PM, Dean Kent wrote:
I spent a bit of time playing with chatGPT to see what it could 
do.   So did my two sons - one an MS in biotech, the other a 
PhD in theoretical physics.    We all came to the same 
conclusion - chatGPT is a very, very good Google search that 
can filter many different possible 'answers' and come to one 
that is 'most likely' based on various factors.  It has little 
to no creativity or understanding of what it is asked to do.   
Not surprising, but different than what the popular press seems 
to say about it.


One of my questions was to write a simple sort routine in 
HLASM. It came back with a template containing the entry/exit 
code, and then a comment *insert sort routine here*.    After 
doing that with many different simple tasks, I came to the 
conclusion that the problem chatGPT has with assembler (but not 
with C, Python, Java, etc.) is that there are so few searchable 
examples of code in assembler.    So the quality of the 
results, for any question, depends upon what exists out on the 
Internet.   Again, not surprising.


As another example, I have an interest in what is called 
'historical analysis'.   There are a number of books on the 
subject, so I asked chatGPT to compare/contrast two of the 
books.   Then two other books, etc.    In literally every case 
it came back with the same introductory text and conclusion - 
but inserted a couple of paragraphs that was similar to a book 
review for each book and compared the 'differences'.   Not very 
impressed.


My PhD son uses it to find obscure hypotheses and formulas that 
would otherwise require a great many hours (or days) of 
searching.   My MS son uses it in a similar fashion to ferret 
out alternative options for the various cell growing and 
protein extraction for his job.   A very useful tool, but not 
yet SkyNet...


YMMV.

On 9/5/2023 9:36 AM, Bill Johnson wrote:
We are all retired. The other 2 went before me. I went in 
July 2022. You’re an idiot regardless. What are you afraid of? 
That a computer can do what you do? That your “skills” aren’t 
all that impressive and can be automated away?



Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:


Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the 
IEFUSI fix it?
Probably because you don't have the wherewithal (even with 2 
helpers).


Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:
Lol, how about going to chatgpt and asking the same question. 
So that cut and paste isn’t a factor.



Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:


Hi Steve,
It won't. The first executable statement is missing a comma 
between

operands.

Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one 
reason or

another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are 
being used.


Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:
You're right, Tom. That is not a program. Certainly not one 
that will

do what it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
 wrote:
I can't be sure I formatted it properly, but after looking 
over the

code, I have nothing to say but WTF? 

     PRINT NOGEN
     TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1 DS    F First input number
NUM2 DS    F Second input number
RESULT   DS    F Result of addition
** Main program
*
MAIN C  0    NUM1   Check if NUM1 is zero
     BE ZERO    Branch to ZERO if true
** Read the first number from input
*
     GET    NUM1,NUMIN  Read NUM1 from input
     LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
     GET    NUM2,NUMIN  Read NUM2 from input
     A  NUM1,NUM2   Add NUM1 and NUM2
     ST

Re: Simple request from chatGPT to write assembler program.

On Tue, 5 Sep 2023 11:27:15 -0700, Tom Brennan wrote:

>Which is a bit strange, because I would expect that every ASM program
>ChatGPT looked at would have had something for that at the top and
>bottom, even if it was just ENTRY/EXIT macros or similar.
>
>On 9/5/2023 11:10 AM, David Spiegel wrote:
>> Hi Tom,
>> It looks like ChatGPT is not aware of "Housekeeping".
>>
Compare to (with no macros) and no formatting problem:
Sender:  IBM Mainframe Assembler List 
Subject: ChatGPT "knows" HLASM
From:  John McKown
Date:  Thu, 1 Jun 2023 12:39:34 -0500

Back when ASSEMBLER-LIST was alive.
-- 
gil 

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Which is a bit strange, because I would expect that every ASM program 
ChatGPT looked at would have had something for that at the top and 
bottom, even if it was just ENTRY/EXIT macros or similar.


On 9/5/2023 11:10 AM, David Spiegel wrote:

Hi Tom,
It looks like ChatGPT is not aware of "Housekeeping".

Regards,
David

On 2023-09-05 13:47, Tom Brennan wrote:
GET and PUT use R14, so as Tom Marchant said, if the program managed 
to get that far it would never return to the OS.


On 9/5/2023 10:21 AM, Paul Gilmartin wrote:

On Tue, 5 Sep 2023 11:34:13 -0500, Tom Marchant  wrote:


    [if]  it made it to the BR 14, it would loop.

???  Rather, that appears to be one of the few correct instructions. 
If R14 hasn't

been modified since entry, it returns to caller.


   SR 15,15 Set return code to 0
   BR 14  Return to caller




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Hi Tom,
It looks like ChatGPT is not aware of "Housekeeping".

Regards,
David

On 2023-09-05 13:47, Tom Brennan wrote:
GET and PUT use R14, so as Tom Marchant said, if the program managed 
to get that far it would never return to the OS.


On 9/5/2023 10:21 AM, Paul Gilmartin wrote:

On Tue, 5 Sep 2023 11:34:13 -0500, Tom Marchant  wrote:


    [if]  it made it to the BR 14, it would loop.

???  Rather, that appears to be one of the few correct instructions.  
If R14 hasn't

been modified since entry, it returns to caller.


   SR 15,15 Set return code to 0
   BR 14  Return to caller




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

GET and PUT use R14, so as Tom Marchant said, if the program managed to 
get that far it would never return to the OS.


On 9/5/2023 10:21 AM, Paul Gilmartin wrote:

On Tue, 5 Sep 2023 11:34:13 -0500, Tom Marchant  wrote:


[if]  it made it to the BR 14, it would loop.


???  Rather, that appears to be one of the few correct instructions.  If R14 
hasn't
been modified since entry, it returns to caller.


   SR 15,15   Set return code to 0
   BR 14  Return to caller




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Tue, 5 Sep 2023 11:34:13 -0500, Tom Marchant  wrote:

>[if]  it made it to the BR 14, it would loop.
>
???  Rather, that appears to be one of the few correct instructions.  If R14 
hasn't
been modified since entry, it returns to caller.

   SR 15,15   Set return code to 0
   BR 14  Return to caller

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Tue, 5 Sep 2023 10:20:20 -0500, Tom Marchant wrote:

>You're right, Tom. That is not a program. Certainly not one that will do what 
>it claims to do.
> 
Mostly right.  A private maaclib might make it come closet.  Suppose the 
private GET
reads a floating point number from a POSIX descriptor.

But plenty other things are wrong.  Is it at least syntactically valid with?  
It has
addressability problems.  It's better than I'd expect if chatGPT has no system 
to test on.

>...
>>*
>>NUM1 DSF First input number
>>...
>>  GETNUM1,NUMIN  Read NUM1 from input
>>...
>>NUMINDCF'0'   Input buffer for numbers

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Matt Hogstrom

Concur Dean.  Its power is that it can search all of its processed content fast 
and give a reasonable response that people can read.  

I think the real threat from AI is bad actors that use that data for nefarious 
purposes.  All tech that we have can be used for good or evil.  The problem is 
that bad actors will use the tech for their purposes.  Its no different than 
cars, chainsaw or firearms.  People can use them for good or not.   It’s no the 
tech; it’s the people.

Yes, it sucks at writing HLASM for the reasons you outlined.  Not enough 
examples or context out there.

Matt Hogstrom
PGP key 0F143BC1

> On Sep 5, 2023, at 10:50, Dean Kent  wrote:
> 
> YMMV.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-05 Thread Dean Kent

I spent a bit of time playing with chatGPT to see what it could do.   So 
did my two sons - one an MS in biotech, the other a PhD in theoretical 
physics.    We all came to the same conclusion - chatGPT is a very, very 
good Google search that can filter many different possible 'answers' and 
come to one that is 'most likely' based on various factors.  It has 
little to no creativity or understanding of what it is asked to do.   
Not surprising, but different than what the popular press seems to say 
about it.


One of my questions was to write a simple sort routine in HLASM. It came 
back with a template containing the entry/exit code, and then a comment 
*insert sort routine here*.    After doing that with many different 
simple tasks, I came to the conclusion that the problem chatGPT has with 
assembler (but not with C, Python, Java, etc.) is that there are so few 
searchable examples of code in assembler.    So the quality of the 
results, for any question, depends upon what exists out on the 
Internet.   Again, not surprising.


As another example, I have an interest in what is called 'historical 
analysis'.   There are a number of books on the subject, so I asked 
chatGPT to compare/contrast two of the books.   Then two other books, 
etc.    In literally every case it came back with the same introductory 
text and conclusion - but inserted a couple of paragraphs that was 
similar to a book review for each book and compared the 'differences'.   
Not very impressed.


My PhD son uses it to find obscure hypotheses and formulas that would 
otherwise require a great many hours (or days) of searching.   My MS son 
uses it in a similar fashion to ferret out alternative options for the 
various cell growing and protein extraction for his job.   A very useful 
tool, but not yet SkyNet...


YMMV.

On 9/5/2023 9:36 AM, Bill Johnson wrote:

We are all retired. The other 2 went before me. I went in July 2022. You’re an 
idiot regardless. What are you afraid of? That a computer can do what you do? 
That your “skills” aren’t all that impressive and can be automated away?


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the IEFUSI fix it?
Probably because you don't have the wherewithal (even with 2 helpers).

Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:

Lol, how about going to chatgpt and asking the same question. So that cut and 
paste isn’t a factor.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Steve,
It won't. The first executable statement is missing a comma between
operands.

Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one reason or
another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.

Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:

You're right, Tom. That is not a program. Certainly not one that will
do what it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

     PRINT NOGEN
     TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1 DS    F First input number
NUM2 DS    F Second input number
RESULT   DS    F Result of addition
** Main program
*
MAIN C  0    NUM1   Check if NUM1 is zero
     BE ZERO    Branch to ZERO if true
** Read the first number from input
*
     GET    NUM1,NUMIN  Read NUM1 from input
     LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
     GET    NUM2,NUMIN  Read NUM2 from input
     A  NUM1,NUM2   Add NUM1 and NUM2
     ST NUM1,RESULT Store the result in RESULT
** Print the result
*
     PUT    RESULT,NUMOUT   Print the result
** Terminate the program
*
     SR 15,15   Set return code to 0
     BR 14  Return to caller
** Define input and output areas
*
NUMIN    DC    F'0'   Input buffer for numbers
NUMOUT   DC    F'0'   Output buffer for result
ZERO DC    F'0'   Constant zero
     END   MAIN    End of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

No. You are too lazy to verify that what you copied/pasted matched the source 
and you want others to make your argument for you? Not me. I've got work to do.

-- 
Tom Marchant

On Tue, 5 Sep 2023 16:04:05 +, Bill Johnson  wrote:

>Lol, how about going to chatgpt and asking the same question. So that cut and 
>paste isn’t a factor.

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Dave always thinks his ideas are “better”. The sign of a narcissist and if you 
ever interview with or work for this type, get a new job.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the IEFUSI fix it?
Probably because you don't have the wherewithal (even with 2 helpers).

Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:
> Lol, how about going to chatgpt and asking the same question. So that cut and 
> paste isn’t a factor.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
>
> Hi Steve,
> It won't. The first executable statement is missing a comma between
> operands.
>
> Regards,
> David
>
> On 2023-09-05 11:43, Steve Thompson wrote:
>> I doubt it will assemble. And even if it does, the results are
>> unpredictable, other than it will probably ABEND for one reason or
>> another.
>>
>> There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.
>>
>> Me thinks this AI system is confusing a few different assembly
>> languages together. I wonder how close they came for DOS I/O.
>> Steve Thompson
>>
>>
>>
>> On 9/5/2023 11:20 AM, Tom Marchant wrote:
>>> You're right, Tom. That is not a program. Certainly not one that will
>>> do what it claims to do.
>>>
>>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
>>>  wrote:
 I can't be sure I formatted it properly, but after looking over the
 code, I have nothing to say but WTF? 

    PRINT NOGEN
    TITLE 'Simple Addition Program'
 ** Define storage for input numbers and result
 *
 NUM1 DS    F First input number
 NUM2 DS    F Second input number
 RESULT   DS    F Result of addition
 ** Main program
 *
 MAIN C  0    NUM1   Check if NUM1 is zero
    BE ZERO    Branch to ZERO if true
 ** Read the first number from input
 *
    GET    NUM1,NUMIN  Read NUM1 from input
    LA 0,NUM1  Load NUM1 into register
 ** Read the second number from input
 *
    GET    NUM2,NUMIN  Read NUM2 from input
    A  NUM1,NUM2   Add NUM1 and NUM2
    ST NUM1,RESULT Store the result in RESULT
 ** Print the result
 *
    PUT    RESULT,NUMOUT   Print the result
 ** Terminate the program
 *
    SR 15,15   Set return code to 0
    BR 14  Return to caller
 ** Define input and output areas
 *
 NUMIN    DC    F'0'   Input buffer for numbers
 NUMOUT   DC    F'0'   Output buffer for result
 ZERO DC    F'0'   Constant zero
    END   MAIN    End of program
>>> --
>>> For IBM-MAIN subscribe / signoff / archive access instructions,
>>> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Bill, formatting or not, the program makes no sense.  Anyone who has 
taken even a couple of ASM classes would know the BE ZERO alone makes no 
sense, branching to a constant F'0'?  Good luck.


Then the GET "DCB" is a DC fullword instead of a DCB.  So that would be 
fun since GET expects a branch address off the DCB from OPEN, and oops, 
there's no OPEN anyway.  Then even if the GET worked and you managed to 
get a 4 byte binary number into NUM1, what in the world is the LA doing, 
trying to load that 4 byte number into register zero?  Just nuts.


I don't need to look any further.  Like I say, anybody who knows even 
the least bit about ASM coding would not even bother trying to assemble 
it.  The code is totally worthless.


On 9/5/2023 9:00 AM, Bill Johnson wrote:

Why do you doubt it? Is it because you hope it doesn’t? Certainly, one of you 
assembler geniuses could test it.

Like Mullins said, and others mentioned, most companies that run z/OS don’t 
need assembler programmers. That numbers in the thousands if not ten thousand. 
Whereas ISV’s who are the likely users of Assembler programming, number in the 
hundreds, maybe. So install on Systems Programmers.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson  wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one reason
or another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being
used.

Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:

You're right, Tom. That is not a program. Certainly not one that will do what 
it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

           PRINT NOGEN
           TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1    DS    F            First input number
NUM2    DS    F            Second input number
RESULT  DS    F            Result of addition
** Main program
*
MAIN    C      0        NUM1  Check if NUM1 is zero
           BE    ZERO            Branch to ZERO if true
** Read the first number from input
*
           GET    NUM1,NUMIN      Read NUM1 from input
           LA    0,NUM1          Load NUM1 into register
** Read the second number from input
*
           GET    NUM2,NUMIN      Read NUM2 from input
           A      NUM1,NUM2      Add NUM1 and NUM2
           ST    NUM1,RESULT    Store the result in RESULT
** Print the result
*
           PUT    RESULT,NUMOUT  Print the result
** Terminate the program
*
           SR    15,15          Set return code to 0
           BR    14              Return to caller
** Define input and output areas
*
NUMIN    DC    F'0'          Input buffer for numbers
NUMOUT  DC    F'0'          Output buffer for result
ZERO    DC    F'0'          Constant zero
           END  MAIN            End of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

We are all retired. The other 2 went before me. I went in July 2022. You’re an 
idiot regardless. What are you afraid of? That a computer can do what you do? 
That your “skills” aren’t all that impressive and can be automated away?


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:25 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the IEFUSI fix it?
Probably because you don't have the wherewithal (even with 2 helpers).

Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:
> Lol, how about going to chatgpt and asking the same question. So that cut and 
> paste isn’t a factor.
>
>
> Sent from Yahoo Mail for iPhone
>
>
> On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
> <0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:
>
> Hi Steve,
> It won't. The first executable statement is missing a comma between
> operands.
>
> Regards,
> David
>
> On 2023-09-05 11:43, Steve Thompson wrote:
>> I doubt it will assemble. And even if it does, the results are
>> unpredictable, other than it will probably ABEND for one reason or
>> another.
>>
>> There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.
>>
>> Me thinks this AI system is confusing a few different assembly
>> languages together. I wonder how close they came for DOS I/O.
>> Steve Thompson
>>
>>
>>
>> On 9/5/2023 11:20 AM, Tom Marchant wrote:
>>> You're right, Tom. That is not a program. Certainly not one that will
>>> do what it claims to do.
>>>
>>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
>>>  wrote:
 I can't be sure I formatted it properly, but after looking over the
 code, I have nothing to say but WTF? 

    PRINT NOGEN
    TITLE 'Simple Addition Program'
 ** Define storage for input numbers and result
 *
 NUM1 DS    F First input number
 NUM2 DS    F Second input number
 RESULT   DS    F Result of addition
 ** Main program
 *
 MAIN C  0    NUM1   Check if NUM1 is zero
    BE ZERO    Branch to ZERO if true
 ** Read the first number from input
 *
    GET    NUM1,NUMIN  Read NUM1 from input
    LA 0,NUM1  Load NUM1 into register
 ** Read the second number from input
 *
    GET    NUM2,NUMIN  Read NUM2 from input
    A  NUM1,NUM2   Add NUM1 and NUM2
    ST NUM1,RESULT Store the result in RESULT
 ** Print the result
 *
    PUT    RESULT,NUMOUT   Print the result
 ** Terminate the program
 *
    SR 15,15   Set return code to 0
    BR 14  Return to caller
 ** Define input and output areas
 *
 NUMIN    DC    F'0'   Input buffer for numbers
 NUMOUT   DC    F'0'   Output buffer for result
 ZERO DC    F'0'   Constant zero
    END   MAIN    End of program
>>> --
>>> For IBM-MAIN subscribe / signoff / archive access instructions,
>>> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
>
>
>
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I see 8 errors. There might be more. If you were to correct the missing comma 
that David pointed out, it would abend. Probably with a S0C1 on the GET. But if 
those errors were to be corrected and it made it to the BR 14, it would loop.

This is what it does when it decides on the specifications for the program. 
That is the most generous test possible.

-- 
Tom Marchant

On Tue, 5 Sep 2023 11:43:07 -0400, Steve Thompson  wrote:

>I doubt it will assemble. And even if it does, the results are
>unpredictable, other than it will probably ABEND for one reason
>or another.
>
>There are no DCB, OPEN, CLOSE macros while GET and PUT are being
>used.
>
>Me thinks this AI system is confusing a few different assembly
>languages together. I wonder how close they came for DOS I/O.
>Steve Thompson
>
>
>
>On 9/5/2023 11:20 AM, Tom Marchant wrote:
>> You're right, Tom. That is not a program. Certainly not one that will do 
>> what it claims to do.
>>
>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
>>  wrote:
>>> I can't be sure I formatted it properly, but after looking over the
>>> code, I have nothing to say but WTF? 
>>>
>>>   PRINT NOGEN
>>>   TITLE 'Simple Addition Program'
>>> ** Define storage for input numbers and result
>>> *
>>> NUM1 DSF First input number
>>> NUM2 DSF Second input number
>>> RESULT   DSF Result of addition
>>> ** Main program
>>> *
>>> MAIN C  0NUM1   Check if NUM1 is zero
>>>   BE ZEROBranch to ZERO if true
>>> ** Read the first number from input
>>> *
>>>   GETNUM1,NUMIN  Read NUM1 from input
>>>   LA 0,NUM1  Load NUM1 into register
>>> ** Read the second number from input
>>> *
>>>   GETNUM2,NUMIN  Read NUM2 from input
>>>   A  NUM1,NUM2   Add NUM1 and NUM2
>>>   ST NUM1,RESULT Store the result in RESULT
>>> ** Print the result
>>> *
>>>   PUTRESULT,NUMOUT   Print the result
>>> ** Terminate the program
>>> *
>>>   SR 15,15   Set return code to 0
>>>   BR 14  Return to caller
>>> ** Define input and output areas
>>> *
>>> NUMINDCF'0'   Input buffer for numbers
>>> NUMOUT   DCF'0'   Output buffer for result
>>> ZERO DCF'0'   Constant zero
>>>   END   MAINEnd of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Hi Bill,
I have a better idea.
Why don't you and the 2 buddies who helped you modify the IEFUSI fix it?
Probably because you don't have the wherewithal (even with 2 helpers).

Regards,
David

On 2023-09-05 12:04, Bill Johnson wrote:

Lol, how about going to chatgpt and asking the same question. So that cut and 
paste isn’t a factor.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Steve,
It won't. The first executable statement is missing a comma between
operands.

Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:

I doubt it will assemble. And even if it does, the results are
unpredictable, other than it will probably ABEND for one reason or
another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.

Me thinks this AI system is confusing a few different assembly
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:

You're right, Tom. That is not a program. Certainly not one that will
do what it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

   PRINT NOGEN
   TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1 DS    F First input number
NUM2 DS    F Second input number
RESULT   DS    F Result of addition
** Main program
*
MAIN C  0    NUM1   Check if NUM1 is zero
   BE ZERO    Branch to ZERO if true
** Read the first number from input
*
   GET    NUM1,NUMIN  Read NUM1 from input
   LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
   GET    NUM2,NUMIN  Read NUM2 from input
   A  NUM1,NUM2   Add NUM1 and NUM2
   ST NUM1,RESULT Store the result in RESULT
** Print the result
*
   PUT    RESULT,NUMOUT   Print the result
** Terminate the program
*
   SR 15,15   Set return code to 0
   BR 14  Return to caller
** Define input and output areas
*
NUMIN    DC    F'0'   Input buffer for numbers
NUMOUT   DC    F'0'   Output buffer for result
ZERO DC    F'0'   Constant zero
   END   MAIN    End of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Lol, how about going to chatgpt and asking the same question. So that cut and 
paste isn’t a factor.


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 12:02 PM, David Spiegel 
<0468385049d1-dmarc-requ...@listserv.ua.edu> wrote:

Hi Steve,
It won't. The first executable statement is missing a comma between 
operands.

Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:
> I doubt it will assemble. And even if it does, the results are 
> unpredictable, other than it will probably ABEND for one reason or 
> another.
>
> There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.
>
> Me thinks this AI system is confusing a few different assembly 
> languages together. I wonder how close they came for DOS I/O.
> Steve Thompson
>
>
>
> On 9/5/2023 11:20 AM, Tom Marchant wrote:
>> You're right, Tom. That is not a program. Certainly not one that will 
>> do what it claims to do.
>>
>> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan 
>>  wrote:
>>> I can't be sure I formatted it properly, but after looking over the
>>> code, I have nothing to say but WTF? 
>>>
>>>   PRINT NOGEN
>>>   TITLE 'Simple Addition Program'
>>> ** Define storage for input numbers and result
>>> *
>>> NUM1 DS    F First input number
>>> NUM2 DS    F Second input number
>>> RESULT   DS    F Result of addition
>>> ** Main program
>>> *
>>> MAIN C  0    NUM1   Check if NUM1 is zero
>>>   BE ZERO    Branch to ZERO if true
>>> ** Read the first number from input
>>> *
>>>   GET    NUM1,NUMIN  Read NUM1 from input
>>>   LA 0,NUM1  Load NUM1 into register
>>> ** Read the second number from input
>>> *
>>>   GET    NUM2,NUMIN  Read NUM2 from input
>>>   A  NUM1,NUM2   Add NUM1 and NUM2
>>>   ST NUM1,RESULT Store the result in RESULT
>>> ** Print the result
>>> *
>>>   PUT    RESULT,NUMOUT   Print the result
>>> ** Terminate the program
>>> *
>>>   SR 15,15   Set return code to 0
>>>   BR 14  Return to caller
>>> ** Define input and output areas
>>> *
>>> NUMIN    DC    F'0'   Input buffer for numbers
>>> NUMOUT   DC    F'0'   Output buffer for result
>>> ZERO DC    F'0'   Constant zero
>>>   END   MAIN    End of program
>> --
>> For IBM-MAIN subscribe / signoff / archive access instructions,
>> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN
>
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.


Hi Steve,
It won't. The first executable statement is missing a comma between 
operands.


Regards,
David

On 2023-09-05 11:43, Steve Thompson wrote:
I doubt it will assemble. And even if it does, the results are 
unpredictable, other than it will probably ABEND for one reason or 
another.


There are no DCB, OPEN, CLOSE macros while GET and PUT are being used.

Me thinks this AI system is confusing a few different assembly 
languages together. I wonder how close they came for DOS I/O.

Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:
You're right, Tom. That is not a program. Certainly not one that will 
do what it claims to do.


-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan 
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

  PRINT NOGEN
  TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1 DS    F First input number
NUM2 DS    F Second input number
RESULT   DS    F Result of addition
** Main program
*
MAIN C  0    NUM1   Check if NUM1 is zero
  BE ZERO    Branch to ZERO if true
** Read the first number from input
*
  GET    NUM1,NUMIN  Read NUM1 from input
  LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
  GET    NUM2,NUMIN  Read NUM2 from input
  A  NUM1,NUM2   Add NUM1 and NUM2
  ST NUM1,RESULT Store the result in RESULT
** Print the result
*
  PUT    RESULT,NUMOUT   Print the result
** Terminate the program
*
  SR 15,15   Set return code to 0
  BR 14  Return to caller
** Define input and output areas
*
NUMIN    DC    F'0'   Input buffer for numbers
NUMOUT   DC    F'0'   Output buffer for result
ZERO DC    F'0'   Constant zero
  END   MAIN    End of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

Why do you doubt it? Is it because you hope it doesn’t? Certainly, one of you 
assembler geniuses could test it.

Like Mullins said, and others mentioned, most companies that run z/OS don’t 
need assembler programmers. That numbers in the thousands if not ten thousand. 
Whereas ISV’s who are the likely users of Assembler programming, number in the 
hundreds, maybe. So install on Systems Programmers. 


Sent from Yahoo Mail for iPhone


On Tuesday, September 5, 2023, 11:43 AM, Steve Thompson  wrote:

I doubt it will assemble. And even if it does, the results are 
unpredictable, other than it will probably ABEND for one reason 
or another.

There are no DCB, OPEN, CLOSE macros while GET and PUT are being 
used.

Me thinks this AI system is confusing a few different assembly 
languages together. I wonder how close they came for DOS I/O.
Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:
> You're right, Tom. That is not a program. Certainly not one that will do what 
> it claims to do.
>
> -- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan 
>  wrote:
>> I can't be sure I formatted it properly, but after looking over the
>> code, I have nothing to say but WTF? 
>>
>>          PRINT NOGEN
>>          TITLE 'Simple Addition Program'
>> ** Define storage for input numbers and result
>> *
>> NUM1    DS    F            First input number
>> NUM2    DS    F            Second input number
>> RESULT  DS    F            Result of addition
>> ** Main program
>> *
>> MAIN    C      0        NUM1  Check if NUM1 is zero
>>          BE    ZERO            Branch to ZERO if true
>> ** Read the first number from input
>> *
>>          GET    NUM1,NUMIN      Read NUM1 from input
>>          LA    0,NUM1          Load NUM1 into register
>> ** Read the second number from input
>> *
>>          GET    NUM2,NUMIN      Read NUM2 from input
>>          A      NUM1,NUM2      Add NUM1 and NUM2
>>          ST    NUM1,RESULT    Store the result in RESULT
>> ** Print the result
>> *
>>          PUT    RESULT,NUMOUT  Print the result
>> ** Terminate the program
>> *
>>          SR    15,15          Set return code to 0
>>          BR    14              Return to caller
>> ** Define input and output areas
>> *
>> NUMIN    DC    F'0'          Input buffer for numbers
>> NUMOUT  DC    F'0'          Output buffer for result
>> ZERO    DC    F'0'          Constant zero
>>          END  MAIN            End of program
> --
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I doubt it will assemble. And even if it does, the results are 
unpredictable, other than it will probably ABEND for one reason 
or another.


There are no DCB, OPEN, CLOSE macros while GET and PUT are being 
used.


Me thinks this AI system is confusing a few different assembly 
languages together. I wonder how close they came for DOS I/O.

Steve Thompson



On 9/5/2023 11:20 AM, Tom Marchant wrote:

You're right, Tom. That is not a program. Certainly not one that will do what 
it claims to do.

-- Tom Marchant On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan 
 wrote:

I can't be sure I formatted it properly, but after looking over the
code, I have nothing to say but WTF? 

  PRINT NOGEN
  TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*
NUM1 DSF First input number
NUM2 DSF Second input number
RESULT   DSF Result of addition
** Main program
*
MAIN C  0NUM1   Check if NUM1 is zero
  BE ZEROBranch to ZERO if true
** Read the first number from input
*
  GETNUM1,NUMIN  Read NUM1 from input
  LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
  GETNUM2,NUMIN  Read NUM2 from input
  A  NUM1,NUM2   Add NUM1 and NUM2
  ST NUM1,RESULT Store the result in RESULT
** Print the result
*
  PUTRESULT,NUMOUT   Print the result
** Terminate the program
*
  SR 15,15   Set return code to 0
  BR 14  Return to caller
** Define input and output areas
*
NUMINDCF'0'   Input buffer for numbers
NUMOUT   DCF'0'   Output buffer for result
ZERO DCF'0'   Constant zero
  END   MAINEnd of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email tolists...@listserv.ua.edu  with the message: INFO IBM-MAIN


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

You're right, Tom. That is not a program. Certainly not one that will do what 
it claims to do.

-- 
Tom Marchant

On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan  
wrote:

>I can't be sure I formatted it properly, but after looking over the 
>code, I have nothing to say but WTF? :)
>
>  PRINT NOGEN
>  TITLE 'Simple Addition Program'
>** Define storage for input numbers and result
>*
>NUM1 DSF First input number
>NUM2 DSF Second input number
>RESULT   DSF Result of addition
>** Main program
>*
>MAIN C  0NUM1   Check if NUM1 is zero
>  BE ZEROBranch to ZERO if true
>** Read the first number from input
>*
>  GETNUM1,NUMIN  Read NUM1 from input
>  LA 0,NUM1  Load NUM1 into register
>** Read the second number from input
>*
>  GETNUM2,NUMIN  Read NUM2 from input
>  A  NUM1,NUM2   Add NUM1 and NUM2
>  ST NUM1,RESULT Store the result in RESULT
>** Print the result
>*
>  PUTRESULT,NUMOUT   Print the result
>** Terminate the program
>*
>  SR 15,15   Set return code to 0
>  BR 14  Return to caller
>** Define input and output areas
>*
>NUMINDCF'0'   Input buffer for numbers
>NUMOUT   DCF'0'   Output buffer for result
>ZERO DCF'0'   Constant zero
>  END   MAINEnd of program

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-04 Thread Bill Johnson

Interesting 




Automation and technology replacing jobs has long been a conversation in 
Nevada's most populated city. Studies show that between 38% to 65% of jobs 
there could be automated by 2035.




I’m betting the high end.


Sent from Yahoo Mail for iPhone


On Monday, September 4, 2023, 11:23 PM, August Carideo 
 wrote:

https://apple.news/AixoP4CtmQXe5nrEq1l8bCw
Interesting article about AI
Idk how many open link

Get Outlook for iOS<https://aka.ms/o0ukef>

From: IBM Mainframe Discussion List  on behalf of Tom 
Brennan 
Sent: Monday, September 4, 2023 4:48:22 PM
To: IBM-MAIN@LISTSERV.UA.EDU 
Subject: Re: Simple request from chatGPT to write assembler program.

I just moved the cursor to where I thought a line should end and pushed
Return.

On 9/4/2023 11:04 AM, Paul Gilmartin wrote:
> On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan wrote:
>
>> I can't be sure I formatted it properly, ...
>>
> What did you do to fix it?  (List the steps, or did you just retype t?)
>
> Could ChatGPT be instructed to use line breaks and eschew NBSP?
>
>> but after looking over the
>> code, I have nothing to say but WTF? :)
>>
>>          PRINT NOGEN
>>          TITLE 'Simple Addition Program'
>> ** Define storage for input numbers and result
>> *
> Reminds me of a certain physicist's first FORTRAN program.
>
> ChatGPT needs to peruse a QSAM tutorial.
> Could it produce a reentrant version?
> Does it remember in case you ask for a refinement?
>
>> NUM1    DS    F            First input number
>> NUM2    DS    F            Second input number
>> RESULT  DS    F            Result of addition
>> ** Main program
>> *
>> MAIN    C      0        NUM1  Check if NUM1 is zero
>>          BE    ZERO            Branch to ZERO if true
>> ** Read the first number from input
>> *
>>          GET    NUM1,NUMIN      Read NUM1 from input
>>          LA    0,NUM1          Load NUM1 into register
>> ** Read the second number from input
>> *
>>          GET    NUM2,NUMIN      Read NUM2 from input
>>          A      NUM1,NUM2      Add NUM1 and NUM2
>>          ST    NUM1,RESULT    Store the result in RESULT
>> ** Print the result
>> *
>>          PUT    RESULT,NUMOUT  Print the result
>> ** Terminate the program
>> *
>>          SR    15,15          Set return code to 0
>>          BR    14              Return to caller
>> ** Define input and output areas
>> *
>> NUMIN    DC    F'0'          Input buffer for numbers
>> NUMOUT  DC    F'0'          Output buffer for result
>> ZERO    DC    F'0'          Constant zero
>>          END  MAIN            End of program
>>
>> On 9/4/2023 9:57 AM, Paul Gilmartinrwrote:
>>> On Mon, 4 Sep 2023 16:36:14 +, Bill Johnson wrote:
>>>
>>>> William:
>>>>
>>>> Write me an assembler program using high-level assembler for the mainframe.
>>>>
>>> Fix your damn mailer, or throw it away and get one that works!
>>>
>>> In particular, do not use NBSP to format code samples.
>>>
>>>> Chatgpt:
>>>>
>>>> Certainly! Here’s a simple example of a mainframe assembly program written 
>>>> in High-Level Assembler (HLASM) that reads two numbers from input and 
>>>> prints their sum:
>>>>            PRINT NOGEN        TITLE 'Simple Addition Program'** Define 
>>>>storage for input numbers and result*NUM1    DS    F            First input 
>>>>numberNUM2    DS    F            Second input numberRESULT  DS    F         
>>>>   Result of addition** Main program*MAIN    C      0      NUM1  Check if 
>>>>NUM1 is zero        BE    ZERO            Branch to ZERO if true** Read the 
>>>>first number from input*        GET    NUM1,NUMIN      Read NUM1 from input 
>>>>       LA    0,NUM1          Load NUM1 into register** Read the second 
>>>>number from input*        GET    NUM2,NUMIN      Read NUM2 from input       
>>>> A      NUM1,NUM2      Add NUM1 and NUM2        ST    NUM1,RESULT    Store 
>>>>the result in RESULT** Print the result*        PUT    RESULT,NUMOUT  Print 
>>>>the result** Terminate the program*        SR    15,15          Set return 
>>>>code to 0        BR    14              Return to caller** Define input and 
>>>>output areas*NUMIN    DC    F'0'          Input buffer for numbersNUMOUT  
>>>>DC    F'0'          Output buffer for resultZERO    DC    F'0'          
>>>>Constant zero        END  MAIN            En

Re: Simple request from chatGPT to write assembler program.

2023-09-04 Thread August Carideo

https://apple.news/AixoP4CtmQXe5nrEq1l8bCw
Interesting article about AI
Idk how many open link

Get Outlook for iOS<https://aka.ms/o0ukef>

From: IBM Mainframe Discussion List  on behalf of Tom 
Brennan 
Sent: Monday, September 4, 2023 4:48:22 PM
To: IBM-MAIN@LISTSERV.UA.EDU 
Subject: Re: Simple request from chatGPT to write assembler program.

I just moved the cursor to where I thought a line should end and pushed
Return.

On 9/4/2023 11:04 AM, Paul Gilmartin wrote:
> On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan wrote:
>
>> I can't be sure I formatted it properly, ...
>>
> What did you do to fix it?  (List the steps, or did you just retype t?)
>
> Could ChatGPT be instructed to use line breaks and eschew NBSP?
>
>> but after looking over the
>> code, I have nothing to say but WTF? :)
>>
>>   PRINT NOGEN
>>   TITLE 'Simple Addition Program'
>> ** Define storage for input numbers and result
>> *
> Reminds me of a certain physicist's first FORTRAN program.
>
> ChatGPT needs to peruse a QSAM tutorial.
> Could it produce a reentrant version?
> Does it remember in case you ask for a refinement?
>
>> NUM1 DSF First input number
>> NUM2 DSF Second input number
>> RESULT   DSF Result of addition
>> ** Main program
>> *
>> MAIN C  0NUM1   Check if NUM1 is zero
>>   BE ZEROBranch to ZERO if true
>> ** Read the first number from input
>> *
>>   GETNUM1,NUMIN  Read NUM1 from input
>>   LA 0,NUM1  Load NUM1 into register
>> ** Read the second number from input
>> *
>>   GETNUM2,NUMIN  Read NUM2 from input
>>   A  NUM1,NUM2   Add NUM1 and NUM2
>>   ST NUM1,RESULT Store the result in RESULT
>> ** Print the result
>> *
>>   PUTRESULT,NUMOUT   Print the result
>> ** Terminate the program
>> *
>>   SR 15,15   Set return code to 0
>>   BR 14  Return to caller
>> ** Define input and output areas
>> *
>> NUMINDCF'0'   Input buffer for numbers
>> NUMOUT   DCF'0'   Output buffer for result
>> ZERO DCF'0'   Constant zero
>>   END   MAINEnd of program
>>
>> On 9/4/2023 9:57 AM, Paul Gilmartinrwrote:
>>> On Mon, 4 Sep 2023 16:36:14 +, Bill Johnson wrote:
>>>
>>>> William:
>>>>
>>>> Write me an assembler program using high-level assembler for the mainframe.
>>>>
>>> Fix your damn mailer, or throw it away and get one that works!
>>>
>>> In particular, do not use NBSP to format code samples.
>>>
>>>> Chatgpt:
>>>>
>>>> Certainly! Here’s a simple example of a mainframe assembly program written 
>>>> in High-Level Assembler (HLASM) that reads two numbers from input and 
>>>> prints their sum:
>>>>PRINT NOGEN TITLE 'Simple Addition Program'** Define 
>>>> storage for input numbers and result*NUM1 DSF First 
>>>> input numberNUM2 DSF Second input numberRESULT   DS
>>>> F Result of addition** Main program*MAIN C  0  
>>>> NUM1   Check if NUM1 is zero BE ZEROBranch to ZERO 
>>>> if true** Read the first number from input* GETNUM1,NUMIN  
>>>> Read NUM1 from input LA 0,NUM1  Load NUM1 into 
>>>> register** Read the second number from input* GETNUM2,NUMIN
>>>>   Read NUM2 from input A  NUM1,NUM2   Add NUM1 and NUM2
>>>>  ST NUM1,RESULT Store the result in RESULT** Print the result* 
>>>> PUTRESULT,NUMOUT   Print the result** Terminate the program*   
>>>>   SR 15,15   Set return code to 0 BR 14
>>>>   Return to caller** Define input and output areas*NUMINDCF'0' 
>>>>   Input buffer for numbersNUMOUT   DCF'0'   Output 
>>>> buffer for resultZERO DCF'0'   Constant zero END   
>>>> MAINEnd of program
>>>> Please note that this is a simplified example for demonstration purposes. 
>>>> In a real-world scenario, you would need to adapt this code to your 
>>>> specific mainframe environment and requirements. Assembly language 
>>>> programming can be quite complex, so make sure to consult the 
>>>> documentation for your specific mainframe and assembler to ensure 
>>>> compatibility and correctness.
>

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-04 Thread Tom Brennan

I just moved the cursor to where I thought a line should end and pushed 
Return.


On 9/4/2023 11:04 AM, Paul Gilmartin wrote:

On Mon, 4 Sep 2023 10:42:51 -0700, Tom Brennan wrote:


I can't be sure I formatted it properly, ...


What did you do to fix it?  (List the steps, or did you just retype t?)

Could ChatGPT be instructed to use line breaks and eschew NBSP?


but after looking over the
code, I have nothing to say but WTF? :)

  PRINT NOGEN
  TITLE 'Simple Addition Program'
** Define storage for input numbers and result
*

Reminds me of a certain physicist's first FORTRAN program.

ChatGPT needs to peruse a QSAM tutorial.
Could it produce a reentrant version?
Does it remember in case you ask for a refinement?


NUM1 DSF First input number
NUM2 DSF Second input number
RESULT   DSF Result of addition
** Main program
*
MAIN C  0NUM1   Check if NUM1 is zero
  BE ZEROBranch to ZERO if true
** Read the first number from input
*
  GETNUM1,NUMIN  Read NUM1 from input
  LA 0,NUM1  Load NUM1 into register
** Read the second number from input
*
  GETNUM2,NUMIN  Read NUM2 from input
  A  NUM1,NUM2   Add NUM1 and NUM2
  ST NUM1,RESULT Store the result in RESULT
** Print the result
*
  PUTRESULT,NUMOUT   Print the result
** Terminate the program
*
  SR 15,15   Set return code to 0
  BR 14  Return to caller
** Define input and output areas
*
NUMINDCF'0'   Input buffer for numbers
NUMOUT   DCF'0'   Output buffer for result
ZERO DCF'0'   Constant zero
  END   MAINEnd of program

On 9/4/2023 9:57 AM, Paul Gilmartinrwrote:

On Mon, 4 Sep 2023 16:36:14 +, Bill Johnson wrote:


William:

Write me an assembler program using high-level assembler for the mainframe.


Fix your damn mailer, or throw it away and get one that works!

In particular, do not use NBSP to format code samples.


Chatgpt:

Certainly! Here’s a simple example of a mainframe assembly program written in 
High-Level Assembler (HLASM) that reads two numbers from input and prints their 
sum:
           PRINT NOGEN         TITLE 'Simple Addition Program'** Define storage 
for input numbers and result*NUM1     DS    F             First input 
numberNUM2     DS    F             Second input numberRESULT   DS    F          
   Result of addition** Main program*MAIN     C      0      NUM1   Check if 
NUM1 is zero         BE     ZERO            Branch to ZERO if true** Read the 
first number from input*         GET    NUM1,NUMIN      Read NUM1 from input    
     LA     0,NUM1          Load NUM1 into register** Read the second number 
from input*         GET    NUM2,NUMIN      Read NUM2 from input         A      
NUM1,NUM2       Add NUM1 and NUM2         ST     NUM1,RESULT     Store the 
result in RESULT** Print the result*         PUT    RESULT,NUMOUT   Print the 
result** Terminate the program*         SR     15,15           Set return code 
to 0         BR     14              Return to caller** Define input and output 
areas*NUMIN    DC    F'0'           Input buffer for numbersNUMOUT   DC    F'0' 
          Output buffer for resultZERO     DC    F'0'           Constant zero   
      END   MAIN            End of program
Please note that this is a simplified example for demonstration purposes. In a 
real-world scenario, you would need to adapt this code to your specific 
mainframe environment and requirements. Assembly language programming can be 
quite complex, so make sure to consult the documentation for your specific 
mainframe and assembler to ensure compatibility and correctness.




--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

The Devil is in the details; with proper MIME headers the QP would have been 
decipherable. As it is, ...

From: IBM Mainframe Discussion List  on behalf of 
Paul Gilmartin <042bfe9c879d-dmarc-requ...@listserv.ua.edu>
Sent: Monday, September 4, 2023 4:25 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 19:54:56 +, Seymour J Metz wrote:

>The original is the exact octets that chaatGPT gave you. QP encoding is not 
>the original.
>
If ChatGPT identified the recipient as a MUA and honored RFC 822++'s USASCII
requirement, some encoding was necessary after it had made two erroneous
assumptions:
o linebreaks are irrelevant and dispensable
o NBSP is preferable to multiple blanks

--
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 19:54:56 +, Seymour J Metz wrote:

>The original is the exact octets that chaatGPT gave you. QP encoding is not 
>the original.
>
If ChatGPT identified the recipient as a MUA and honored RFC 822++'s USASCII
requirement, some encoding was necessary after it had made two erroneous
assumptions:
o linebreaks are irrelevant and dispensable
o NBSP is preferable to multiple blanks

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

The original is the exact octets that chaatGPT gave you. QP encoding is not 
the original.


From: IBM Mainframe Discussion List  on behalf of 
Paul Gilmartin <042bfe9c879d-dmarc-requ...@listserv.ua.edu>
Sent: Monday, September 4, 2023 3:46 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 18:54:21 +, Seymour J Metz wrote:

>I'd have to view the original in hex before I'd even try to guess.
>
Ask ChatGPT to fix it!

What's "the original"?  Here's what my MUA shows as "Raw Source".
no linebreaks; no trailing spaces; lotsa NBSP:

Chatgpt:

Certainly! Here=E2=80=99s a simple example of a mainframe assembly program =
written in High-Level Assembler (HLASM) that reads two numbers from input a=
nd prints their sum:
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0PRINT NOGEN=C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0TITLE 'Simple Addition Program'** Define storage for input numbers an=
d result*NUM1 =C2=A0 =C2=A0 DS =C2=A0 =C2=A0F =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 First input numberNUM2 =C2=A0 =C2=A0 DS =C2=A0 =C2=A0F =C2=A0=
 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 Second input numberRESULT =C2=A0 DS =C2=
=A0 =C2=A0F =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 Result of addition** =
Main program*MAIN =C2=A0 =C2=A0 C =C2=A0 =C2=A0 =C2=A00 =C2=A0 =C2=A0 =C2=
=A0NUM1 =C2=A0 Check if NUM1 is zero=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0BE =
=C2=A0 =C2=A0 ZERO =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0Branch to ZERO =
if true** Read the first number from input*=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0GET =C2=A0 =C2=A0NUM1,NUMIN =C2=A0 =C2=A0 =C2=A0Read NUM1 from input=C2=
=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0LA =C2=A0 =C2=A0 0,NUM1 =C2=A0 =C2=A0 =C2=A0=
 =C2=A0 =C2=A0Load NUM1 into register** Read the second number from input*=

--
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 18:54:21 +, Seymour J Metz wrote:

>I'd have to view the original in hex before I'd even try to guess. 
>
Ask ChatGPT to fix it!

What's "the original"?  Here's what my MUA shows as "Raw Source".
no linebreaks; no trailing spaces; lotsa NBSP:

Chatgpt:

Certainly! Here=E2=80=99s a simple example of a mainframe assembly program =
written in High-Level Assembler (HLASM) that reads two numbers from input a=
nd prints their sum:
=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0PRINT NOGEN=C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0TITLE 'Simple Addition Program'** Define storage for input numbers an=
d result*NUM1 =C2=A0 =C2=A0 DS =C2=A0 =C2=A0F =C2=A0 =C2=A0 =C2=A0 =C2=A0 =
=C2=A0 =C2=A0 First input numberNUM2 =C2=A0 =C2=A0 DS =C2=A0 =C2=A0F =C2=A0=
 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 Second input numberRESULT =C2=A0 DS =C2=
=A0 =C2=A0F =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 Result of addition** =
Main program*MAIN =C2=A0 =C2=A0 C =C2=A0 =C2=A0 =C2=A00 =C2=A0 =C2=A0 =C2=
=A0NUM1 =C2=A0 Check if NUM1 is zero=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0BE =
=C2=A0 =C2=A0 ZERO =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0Branch to ZERO =
if true** Read the first number from input*=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=
=A0GET =C2=A0 =C2=A0NUM1,NUMIN =C2=A0 =C2=A0 =C2=A0Read NUM1 from input=C2=
=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0LA =C2=A0 =C2=A0 0,NUM1 =C2=A0 =C2=A0 =C2=A0=
 =C2=A0 =C2=A0Load NUM1 into register** Read the second number from input*=

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

I'd have to view the original in hex before I'd even try to guess. 

From: IBM Mainframe Discussion List  on behalf of 
Paul Gilmartin <042bfe9c879d-dmarc-requ...@listserv.ua.edu>
Sent: Monday, September 4, 2023 2:40 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 18:28:35 +, Seymour J Metz wrote:

>I've had situations where pasting to and copying from notepad (not wordpad) 
>fixes similar issues.
>
vi  expanded the NBSP.  Is there a fix for the newlines?

Just give ChatGPT D- and a makeup assignment.

--
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 18:32:29 +, Bill Johnson wrote:

>Not sure. My experience with chatgpt is minimal. I installed it on the iPhone 
>a month or two ago and this is my second attempt to get it to do something. 
>
It's like "Genuine Fractals".  It looks like Assembler code only when viewed 
from afar.

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

On Mon, 4 Sep 2023 18:28:35 +, Seymour J Metz wrote:

>I've had situations where pasting to and copying from notepad (not wordpad) 
>fixes similar issues.
>
vi  expanded the NBSP.  Is there a fix for the newlines?

Just give ChatGPT D- and a makeup assignment.

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.

2023-09-04 Thread Bill Johnson

Not sure. My experience with chatgpt is minimal. I installed it on the iPhone a 
month or two ago and this is my second attempt to get it to do something. 

Sent from Yahoo Mail for iPhone

On Monday, September 4, 2023, 2:25 PM, Paul Gilmartin 
<042bfe9c879d-dmarc-requ...@listserv.ua.edu> wrote:

On Mon, 4 Sep 2023 17:20:24 +, Bill Johnson wrote:

>The formatting was perfect. The cut & paste wasn’t. 
>
Could you direct it to a file instead of the screen, and attach the file?
(Teachers look askance at copies of homework.)

-- 
gil

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN

Re: Simple request from chatGPT to write assembler program.