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

[Martin McClure]

There was a presentation at ESUG about using LLMs to document code, 
which is an interesting use -- take precise code and generate imprecise 
natural language from it. Some kind of neural network (not sure whether 
it would be an LLM) might also be able to improve the accuracy of code 
completion. I'm very leery of AI actually producing code -- it seems 
like whenever I see an AI answer about anything non-trivial, it comes up 
with a very plausible-sounding but completely incorrect answer.

Regards,

-Martin

On 1/4/26 11:30 AM, Michał Olszewski via Cuis-dev wrote:
>
> Hi all,
>
> I'd like to start a loose discussion around trend that has been 
> happening in the past two years, namely using LLM agents for rapidly 
> building prototypes and applications alike (infamously known as "vibe 
> coding" if you don't know what you're doing :). More neutral term is 
> "AI assisted workflow"). The "state of the art" advanced to the point 
> where it's possible to generate, refactor and document entire 
> codebases without a sweat using multi agent workflows, MCP servers, 
> task-oriented instructions etc. - see Claude Code (Sonnet 4.5, Opus 
> 4.5) ecosystem for example [*1*].
>
> Since Smalltalk environments are quite walled gardens (code pretty 
> much lives in the binary image, with attempts from Cuis and others to 
> store packages in textual format) there hasn't been much motion 
> towards integrating LLM workflows with the internal tooling, as it's 
> requires dedicated communication protocol (any packages for that 
> already? :)) and besides that, there wasn't opportunity to train on 
> large chunks of ST sources.
>
> Open ended questions (with my opinion for each of them):
>
>   * given there would be proper integration (fine-tuning, dedicated
>     package for interfacing, set of human-written instructions etc.),
>     what do you think about using LLM agents for: 1) rapid building of
>     prototypes or entire applications 2) progress verification e.g.
>     whether implementation matches functionality spec 3) knowledge
>     finding and example generation? For 1) and 2) see
>     director-implementor pattern [*2*].
>   * do you think Smalltalk-like systems are more suitable for LLMs
>     than file based languages? - The tight integration of tools-system
>     is already there - there is no need to implement heavy MCP servers
>     or RAG, just ask/explore the system for the answer! There is also
>     question about token usage - context windows don't need to store
>     entire text blocks anymore, only relationships provided by the
>     tooling.
>   * given above, would local, task-oriented LLMs provide first class
>     experience for us, just like one-size-fits-all models for the
>     broader world?
>
> References:
>
>  1. https://www.anthropic.com/engineering/claude-code-best-practices
>  2. https://github.com/maxim-ist/elixir-architect/blob/main/skills/elixir-architect/SKILL.md
>
> Cheers,
> Michał
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cuis.st/mailman/archives/cuis-dev/attachments/20260104/d4556f1a/attachment.htm>