[cess11]

"Claude is aware of that, but it struggled to write correct code based on those rules"

It's actually not, and unless they in some way run a rule engine on top of their LLM SaaS stuff it seems far fetched to believe it adheres to rule sets in any way.

Local models confuse Python, Elixir, PHP and Bash when I've tried to use them for coding. They seem more stable for JS, but sometimes they slip out of that too.

Seems pretty contrived and desperate to invent transpilers from quasi-Python to other languages to try and find a software development use for LLM SaaS. Warnings about Lisp macros and other code rewrite tools ought to apply here as well. Plus, of course, the loss of 'notation as a tool of thought'.

[strangescript]

If your model is getting confused by python, its a bad model. Python is routinely the best language for all major models.

[cess11]

I don't know what counts as a major model. Relevant to this, I've dabbled with Gemma, Qwen, Mistral, Llama, Granite and Phi models, mostly 3-14b varieties but also some larger ones on CPU on a machine that has 64 GB RAM.

[wild_egg]

I think the issue there is those smaller versions of those models. I regularly use Gemma3 and Qwen3 for programming without issue but in the 27b-32b range. Going smaller than that generally yields garbage.

[cess11]

I've tried 24-32b sizes as well and besides being even slower they were also unreliable.