So far I have had a 100% failure rate in trying to get Claude or ChatGPT 
help solve small but tricky problems. They have burned up a large number of 
free tokens and made many suggestions but haven't solved the problems.

They also don't seem to have a large enough context window to be able to 
maintain the overall picture of large threads. So I don't see how they 
could be able to create a decent large system design. Just complete enough 
specifications for one component would probably overflow the context window.

Given that we know that good quality and reliable operation cannot be 
achieved by testing alone, I don't see how widespread adoption is going to 
be anything but a long term software nightmare. All these systems that may 
*seem* to work but watch out when they hit edge cases...

On Wednesday, May 13, 2026 at 6:50:42 PM UTC-4 [email protected] wrote:

> Just my two cents on my position about all this "agentic programming 
> fashionware", I don't want to delegate big parts of my understanding of 
> complex systems, including software, to non-deterministic systems that 
> "hallucinate" in non detectable ways. I try to confine the stuff I don't 
> understand about the software artifacts I build to small parts, where I ask 
> specific questions to the AI (or Apparent Intelligence, as I like to call 
> it) and do small commits.
>
> I keep my tokens usage small, use anonymous AI systems like duck.ai or 
> Lumo, that don't use my data for training and I think that in all that rush 
> of AI, seems a minimalist approach with little compromise.
>
> I doubtful and worried of a grandiloquent visions with a 
> unique convergent future for diverse people and worldviews, particularly 
> when it comes from tech bros. Unfortunately "agentic programming" seems one 
> of such visions.
>
> Cheers,
>
> Offray
> On 26/04/26 21:26, Thomas Passin wrote:
>
> I knew about Cyc, of course. I didn't keep up with it but it didn't seem 
> to go anywhere. The quotations from Lenat seem quite apt to me.
>
> On Sunday, April 26, 2026 at 1:44:27 PM UTC-4 David Szent-Györgyi wrote:
>
>> On Sunday, April 26, 2026 at 10:19:49 AM UTC-4 [email protected] wrote:
>>
>> Thanks for posting about  Eurisko. It seems to have passed me by at the 
>> time. Fascinating!
>>
>>
>> I read today that Lenat's follow-on to Eurisko is Cyc, which is described 
>> in an article on Wikipedia <https://en.wikipedia.org/wiki/Cyc>. It 
>> represents knowledge using the formal language CycL 
>> <https://en.wikipedia.org/wiki/CycL>. Lenat died in 2023, the articles 
>> on Cyc and on Lenat have nothing to say about the future of Cyc. 
>>
>> Lenat lived long enough to see the beginnings of the current day advance 
>> of machine learning in the corporate sphere and public life. Two quotations 
>> mentioned in the Wikipeda article on him 
>> <https://en.wikipedia.org/wiki/Douglas_Lenat> seem worth remembering in 
>> light of that advance: 
>>
>> “If computers were human, they’d present themselves as autistic, 
>> schizophrenic, or otherwise brittle. It would be unwise or dangerous for 
>> that person to take care of children and cook meals, but it’s on the 
>> horizon for home robots. That’s like saying, ‘We have an important job to 
>> do, but we’re going to hire dogs and cats to do it.'.'” 
>> - from 2014 <https://www.businessinsider.com/cycorp-ai-2014-7>
>>
>> "Sometimes the *veneer* of intelligence is not enough."
>> - from 2017 
>> <https://cognitiveworld.com/article/sometimes-veneer-intelligence-not-enough>
>>
> -- 
> You received this message because you are subscribed to the Google Groups 
> "leo-editor" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to [email protected].
> To view this discussion visit 
> https://groups.google.com/d/msgid/leo-editor/61ec3877-0a0a-4960-a0e1-0303c747635en%40googlegroups.com
>  
> <https://groups.google.com/d/msgid/leo-editor/61ec3877-0a0a-4960-a0e1-0303c747635en%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>
>

-- 
You received this message because you are subscribed to the Google Groups 
"leo-editor" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion visit 
https://groups.google.com/d/msgid/leo-editor/d3d33534-a869-4d5e-9d92-5934d7801eeen%40googlegroups.com.

Reply via email to