Re: [GTALUG] "AI" on getting correct technical answers
On Sun, Jan 14, 2024 at 7:20 AM o1bigtenor via talk wrote: > On Sun, Jan 14, 2024 at 3:06 AM ac via talk wrote: > > > snip > > > > And, it's just a generic LLM. I've heard experienced developers > > > saying surprisingly positive things about GitHub's Copilot for quite > > > a while now. > > > As for the SQL issue - all search queries on Qwant / DDG / Google > > > lead to "how to join tables in SQL"; utterly useless. I know that > > > reasonably well. > > > And, who hasn't had a search lead them to StackOverflow where the > > > highest rated answer is strongly condemned further in the comments as > > > being wrong / out of date / insecure, etc.? > > > > > Actually, this is an interesting point. > > > > Google search seems to prioritise answers from humans and human sources. > > > > I searched on Microsoft the other day and was surprised to see that I > > could supply .js snippets (which I did not code and was too lazy to > > read through) and receive a correct answer direct from "search" > > > > So, us humans will be replaced as 'coders" - Machines will be writing > > the code which powers machines. Not only is that something for us to > > understand fully, but we also have to comprehend where we are all > > choosing to go. > > > > It is like watching episodes of "the Traitors" and seeing how the > > majority votes out a faithful. > > > > there is just nothing to do but be along for the ride :) > > > > > Lots of incorrect answers supplied by humans. > > > > > indeed, if only there was some way to 'sort' or use advanced search to > > set dates... (to exclude popular answers from 2009) or do more settings > > on search options... oh, wait - and then there are no search > > results... when is "search" not "search" and just becomes "answer" - > > interesting! - it is like a mobile phone - it is hardly even a mobile > > phone any longer, why do so many people still call it a 'phone' or a > > mobile phone... > > > > I think though that I will still be using Google for search, although > > when looking at it all from my perspective we are all already screwed, > > unless we can vote out all of the tratitors. (which seems increasingly > > unlikely) > > > Re: search engines - - - - to me they are totally frustrating. > > If I'm asking for a search where I want terms 'a + b + c + d + e' well - > I'm looking for where ALL 5 terms show up. Not where any one term is or > any two (etc etc). So if one is looking for very generic kind of items - - > well search is useful - - - if you're looking for the specific - - - - > search > - - - well - - its quite useless! > > (tried to sign up for chatgpt but as I'm unable to use a cellphone at my > location that's a no for even signup (and no way to reach the idiots - - > - - sorry I guess I should use people but I wonder - - to let them know > that I can't because its only after registration that connection is > allowed - - - total circular logic that is!) I'm having a hard time parsing this. I have never used a cellphone to access https://chat.openai.com -- this is where I signed up for free and later where I upgraded to Plus. The process to register is quite easy, I don't quite understand the issues you and Kevin are having. FWIW, I have had generally good results with ChatGPT4 with two exceptions: - It's awful at anything location-based - fine for solutions, not fine for opinions - Evan --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] "AI" on getting correct technical answers
On 2024-01-14 07:19, o1bigtenor via talk wrote: Re: search engines - - - - to me they are totally frustrating. If I'm asking for a search where I want terms 'a + b + c + d + e' well - I'm looking for where ALL 5 terms show up. Not where any one term is or any two (etc etc). So if one is looking for very generic kind of items Most search engine in general seem rather poor. Google used to be better. IIRC, there was a time when you could do a search using a phrase, or tell it which words were required to be in the search result. I find most search engines on web sites seem to return any page containing any of the words you provide. -- Cheers! Kevin. https://www.patreon.com/KevinCozens | "Nerds make the shiny things that | distract the mouth-breathers, and Owner of Elecraft K2 #2172 | that's why we're powerful" #include | --Chris Hardwick --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] AI - Llama 2 an open source AI that can run on a Raspberry PI
On Sun, Jan 14, 2024 at 7:31 AM Colin McGregor wrote: > > Okay, so obvious next question, what fully open alternatives are > currently available for Llama 2 and if there are none what can we do > to help create such an alternative? > Right now the community involved in advancing "Open AI" is still in the definition phase, trying to determine what that means. One could do worse than look at the progress made along this path: https://blog.opensource.org/closing-the-2023-rounds-of-deep-dive-ai-with-first-draft-piece-of-the-definition-of-open-source-ai/ One of the primary movers of this effort will be speaking at the February meeting of GTALUG. - Evan --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] "AI" on getting correct technical answers
ChatGPT is very good at making up stories to amuse my female friends. Ask
it to write a love poem to a girl and she will be thrilled at the result.
There is no verification or source required. ChatGPT is good for chatting.
I find its Chinese is also very good. You can use ChatGPT to improve their
English level for learners. There are a lot of benefits to the tech, but
factual accuracy is not one of them.
On a Chinese social media platform I asked ChatGPT (the company is based in
sunny California) where it was from. It said that it was from Huan, China,
but then could/would not tell me where in Hunan was its home town.
On Sun, 14 Jan 2024 at 07:26, o1bigtenor via talk wrote:
> On Sun, Jan 14, 2024 at 3:06 AM ac via talk wrote:
> >
> snip
>
> > > And, it's just a generic LLM. I've heard experienced developers
> > > saying surprisingly positive things about GitHub's Copilot for quite
> > > a while now.
> > > As for the SQL issue - all search queries on Qwant / DDG / Google
> > > lead to "how to join tables in SQL"; utterly useless. I know that
> > > reasonably well.
> > > And, who hasn't had a search lead them to StackOverflow where the
> > > highest rated answer is strongly condemned further in the comments as
> > > being wrong / out of date / insecure, etc.?
> > >
> > Actually, this is an interesting point.
> >
> > Google search seems to prioritise answers from humans and human sources.
> >
> > I searched on Microsoft the other day and was surprised to see that I
> > could supply .js snippets (which I did not code and was too lazy to
> > read through) and receive a correct answer direct from "search"
> >
> > So, us humans will be replaced as 'coders" - Machines will be writing
> > the code which powers machines. Not only is that something for us to
> > understand fully, but we also have to comprehend where we are all
> > choosing to go.
> >
> > It is like watching episodes of "the Traitors" and seeing how the
> > majority votes out a faithful.
> >
> > there is just nothing to do but be along for the ride :)
> >
> > > Lots of incorrect answers supplied by humans.
> > >
> > indeed, if only there was some way to 'sort' or use advanced search to
> > set dates... (to exclude popular answers from 2009) or do more settings
> > on search options... oh, wait - and then there are no search
> > results... when is "search" not "search" and just becomes "answer" -
> > interesting! - it is like a mobile phone - it is hardly even a mobile
> > phone any longer, why do so many people still call it a 'phone' or a
> > mobile phone...
> >
> > I think though that I will still be using Google for search, although
> > when looking at it all from my perspective we are all already screwed,
> > unless we can vote out all of the tratitors. (which seems increasingly
> > unlikely)
> >
> Re: search engines - - - - to me they are totally frustrating.
>
> If I'm asking for a search where I want terms 'a + b + c + d + e' well -
> I'm looking for where ALL 5 terms show up. Not where any one term is or
> any two (etc etc). So if one is looking for very generic kind of items - -
> well search is useful - - - if you're looking for the specific - - - -
> search
> - - - well - - its quite useless!
>
> As I've been pondering the AI stuff (tried to sign up for chatgpt but as
> I'm
> unable to use a cellphone at my location that's a no for even signup (and
> no way to reach the idiots - - - - sorry I guess I should use people but I
> wonder - - to let them know that I can't because its only after
> registration
> that connection is allowed - - - total circular logic that is!) what
> I've come up
> with is from looking at the past.
>
> Truly innovative and unique ideas/things are rarely enough even designed
> or developed by a 'team' (that's changing in advanced materials these days
> though) most often its an individual that finds something that the
> thundering
> herd has either ignored or doesn't know about. Somehow to date AI is more
> about the thundering herd (and a technique that when fully utilized will
> allow
> major chip makers (and some small group of other hardware vendors) to
> really cache in the bucks ('Follow the money' is the adage!). Am wondering
> if that is the reason for AI's proliferation?
>
> What say you?
>
> TIA
> ---
> Post to this mailing list talk@gtalug.org
> Unsubscribe from this mailing list
> https://gtalug.org/mailman/listinfo/talk
>
---
Post to this mailing list talk@gtalug.org
Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] "AI" on getting correct technical answers
On 2024-01-13 10:30, Ron / BCLUG via talk wrote: Alvin Starr via talk wrote on 2024-01-12 20:11: It is defiantly not useful for getting correct technical answers to problems. That's not my experience. I guess that depends on the definition of "correct technical answers", because it (i.e. ChatGPT) can be excellent at giving correct answers to technical (coding) problems. I haven't tried ChatGPT due to the registration process but I have tried one or two of the other equivalents. I've found them to be useless to any of the technical (mostly coding related) questions I've asked. Apparently I'm not asking the right questions. :) -- Cheers! Kevin. https://www.patreon.com/KevinCozens | "Nerds make the shiny things that | distract the mouth-breathers, and Owner of Elecraft K2 #2172 | that's why we're powerful" #include | --Chris Hardwick --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] "AI" on getting correct technical answers
On Sun, Jan 14, 2024 at 3:06 AM ac via talk wrote:
>
snip
> > And, it's just a generic LLM. I've heard experienced developers
> > saying surprisingly positive things about GitHub's Copilot for quite
> > a while now.
> > As for the SQL issue - all search queries on Qwant / DDG / Google
> > lead to "how to join tables in SQL"; utterly useless. I know that
> > reasonably well.
> > And, who hasn't had a search lead them to StackOverflow where the
> > highest rated answer is strongly condemned further in the comments as
> > being wrong / out of date / insecure, etc.?
> >
> Actually, this is an interesting point.
>
> Google search seems to prioritise answers from humans and human sources.
>
> I searched on Microsoft the other day and was surprised to see that I
> could supply .js snippets (which I did not code and was too lazy to
> read through) and receive a correct answer direct from "search"
>
> So, us humans will be replaced as 'coders" - Machines will be writing
> the code which powers machines. Not only is that something for us to
> understand fully, but we also have to comprehend where we are all
> choosing to go.
>
> It is like watching episodes of "the Traitors" and seeing how the
> majority votes out a faithful.
>
> there is just nothing to do but be along for the ride :)
>
> > Lots of incorrect answers supplied by humans.
> >
> indeed, if only there was some way to 'sort' or use advanced search to
> set dates... (to exclude popular answers from 2009) or do more settings
> on search options... oh, wait - and then there are no search
> results... when is "search" not "search" and just becomes "answer" -
> interesting! - it is like a mobile phone - it is hardly even a mobile
> phone any longer, why do so many people still call it a 'phone' or a
> mobile phone...
>
> I think though that I will still be using Google for search, although
> when looking at it all from my perspective we are all already screwed,
> unless we can vote out all of the tratitors. (which seems increasingly
> unlikely)
>
Re: search engines - - - - to me they are totally frustrating.
If I'm asking for a search where I want terms 'a + b + c + d + e' well -
I'm looking for where ALL 5 terms show up. Not where any one term is or
any two (etc etc). So if one is looking for very generic kind of items - -
well search is useful - - - if you're looking for the specific - - - - search
- - - well - - its quite useless!
As I've been pondering the AI stuff (tried to sign up for chatgpt but as I'm
unable to use a cellphone at my location that's a no for even signup (and
no way to reach the idiots - - - - sorry I guess I should use people but I
wonder - - to let them know that I can't because its only after registration
that connection is allowed - - - total circular logic that is!) what
I've come up
with is from looking at the past.
Truly innovative and unique ideas/things are rarely enough even designed
or developed by a 'team' (that's changing in advanced materials these days
though) most often its an individual that finds something that the thundering
herd has either ignored or doesn't know about. Somehow to date AI is more
about the thundering herd (and a technique that when fully utilized will allow
major chip makers (and some small group of other hardware vendors) to
really cache in the bucks ('Follow the money' is the adage!). Am wondering
if that is the reason for AI's proliferation?
What say you?
TIA
---
Post to this mailing list talk@gtalug.org
Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] AI - Llama 2 an open source AI that can run on a Raspberry PI
On Sat, Jan 13, 2024 at 5:39 AM Evan Leibovitch wrote: > > On Wed, Jan 10, 2024 at 10:47 AM Colin McGregor via talk > wrote: >> >> As noted last evening I am running the open source (but NOT GPL) Llama >> 2 AI on a Raspberry PI 5. > > > As discussed at the meeting Tuesday night, Llama 2 is not Open Source. It > conforms to neither the OSI Open Source Definition nor the FSF Four Freedoms. > This post from IBM explains how and why it's not: > https://www.ibm.com/topics/llama-2#Is+Llama+2+open+source? > > While the license is broadly open, it's not open source or free software in > much the same way as the Creative Commons "NC" license is not; it restricts > use and requires certain entities to get a paid license. Okay, so obvious next question, what fully open alternatives are currently available for Llama 2 and if there are none what can we do to help create such an alternative? Colin. > - Evan > --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
Re: [GTALUG] "AI" on getting correct technical answers
On Sat, 13 Jan 2024 07:30:29 -0800 Ron / BCLUG via talk wrote: > Alvin Starr via talk wrote on 2024-01-12 20:11: > > It is defiantly not useful for getting correct technical answers to > > problems. > agreed. It is accurate when you provide it with code. or actual copy & paste of something you are working with so that it can parse what you are doing wrong or run it's own code on your issue. solving many different types of technical issues it is as useless as search could potentially be and sometimes more so as it could quite convincingly send you on arbitrary solutions that turn out to be completely incorrect. > That's not my experience. > it depends on the technical problem. "AI" does somewhat suck at certain type of problems. Where a coding type "problem" is a shortage of "experience", skill or knowledge type problem, it is quite accurate, in my experience. try asking it about technical problems related to many types of error messages in server logs... try asking it many different types of technical questions where humans generated the issue or where humans are involved in the technical cause for failure. > I guess that depends on the definition of "correct technical > answers", because it (i.e. ChatGPT) can be excellent at giving > correct answers to technical (coding) problems. > yes, more so accurate if you feed the code (or examples of the code) but - it is not always the most efficient or the "best" solution, but I do agree that it has been a working solution > > Got an SQL problem that requires a contrived joining of multiple > tables and have tried every left-join / right-join, CTE / subquery > combo and just can't get it to work after *hours* of trying? > Feed the problem into ChatGPT and get a correct answer in seconds. > Got some weird behaviour in JS where asynchronous code and variable > scoping issues are colliding to give weird behaviour? > Feed the code to ChatGPT, ask "what's wrong", and have it spit out > corrected code *AND* and explanation of what's wrong with the code it > was provided. > Stunning. good to know, I have not tried feeding it SQL yet, this is actually a good idea and something to remember > And, it's just a generic LLM. I've heard experienced developers > saying surprisingly positive things about GitHub's Copilot for quite > a while now. > As for the SQL issue - all search queries on Qwant / DDG / Google > lead to "how to join tables in SQL"; utterly useless. I know that > reasonably well. > And, who hasn't had a search lead them to StackOverflow where the > highest rated answer is strongly condemned further in the comments as > being wrong / out of date / insecure, etc.? > Actually, this is an interesting point. Google search seems to prioritise answers from humans and human sources. I searched on Microsoft the other day and was surprised to see that I could supply .js snippets (which I did not code and was too lazy to read through) and receive a correct answer direct from "search" So, us humans will be replaced as 'coders" - Machines will be writing the code which powers machines. Not only is that something for us to understand fully, but we also have to comprehend where we are all choosing to go. It is like watching episodes of "the Traitors" and seeing how the majority votes out a faithful. there is just nothing to do but be along for the ride :) > Lots of incorrect answers supplied by humans. > indeed, if only there was some way to 'sort' or use advanced search to set dates... (to exclude popular answers from 2009) or do more settings on search options... oh, wait - and then there are no search results... when is "search" not "search" and just becomes "answer" - interesting! - it is like a mobile phone - it is hardly even a mobile phone any longer, why do so many people still call it a 'phone' or a mobile phone... I think though that I will still be using Google for search, although when looking at it all from my perspective we are all already screwed, unless we can vote out all of the tratitors. (which seems increasingly unlikely) > > rb > > --- > Post to this mailing list talk@gtalug.org > Unsubscribe from this mailing list > https://gtalug.org/mailman/listinfo/talk --- Post to this mailing list talk@gtalug.org Unsubscribe from this mailing list https://gtalug.org/mailman/listinfo/talk
