[Cuis-dev] [Loose Discussion] LLM agents in Smalltalk

[Phil B]

Current LLMs aren't that smart.  They're purely tokens in, tokens out with
no real structural understanding.  The idea of RAG is to inject the LLM
with the knowledge needed for a given prompt to give a good answer without
additional training required.

On Sat, Jan 10, 2026 at 2:53 PM Hilaire Fernandes via Cuis-dev <
cuis-dev at lists.cuis.st> wrote:

> I am wondering if LiveTyping could not be a leveler to add object semantic
> while training an AI.
>
> Hilaire
> Le 05/01/2026 à 00:12, Phil B via Cuis-dev a écrit :
>
> If you're thinking about anything serious with an LLM, I think you're
> going to want to go with a RAG solution that feeds in code from the image
> as well as other relevant code (from Smalltalk as well as other languages)
> and other information for what you are working on.  Could you feed in just
> the code from a Smalltalk image into a 1 million+ token context window?
> Sure, but I don't think you'd get nearly the results you're expecting...
> unless you're doing image development rather than application/library
> development.  I have gotten some stunning results with RAG-based systems
> and lesser used programming languages/libraries precisely because the RAG
> environment had comprehensive coverage of how to solve problems in other
> languages and it was able to translate the answer in my target language.
>
> -- http://mamot.fr/@drgeo
>
> --
> Cuis-dev mailing list
> Cuis-dev at lists.cuis.st
> https://lists.cuis.st/mailman/listinfo/cuis-dev
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cuis.st/mailman/archives/cuis-dev/attachments/20260110/ad7e3f9d/attachment.htm>