If you want the model to have function calls available you need to run it in an agentic harness that can do the proper sandboxing etc. to keep things safe and provide the spec and syntax in your system prompt. This is true of any model: AI inference on its own can only involve guessing, not exact compute.

▲

neonstatic 2 days ago | parent [-]

Thanks, I am very new to this and just run models in LMStudio. I think it would be very useful to have a system prompt telling the model to run python scripts to calculate things LLMs are particularly bad at and run those scripts. Can you recommend a harness that you like to use? I suppose safety of these solutions is its own can of worms, but I am willing to try it.

▲

Computer0 2 days ago | parent [-]

I use Claude Code. Codex and Opencode both work too. You could even do it with VScode Copilot.

▲

zozbot234 2 days ago | parent [-]

These are typically coding oriented as opposed to general chat, so their system prompts may be needlessly heavy for that use case. I think the closest thing to a general solution is the emerging "claw" ecosystem, as silly as that sounds. Some of the newer "claws" do provide proper sandboxing.

▲

kristopolous a day ago | parent [-]

This is actually a perfect use case of my llcat ... Using Unix philosophy for the llm era

https://github.com/day50-dev/llcat

I've got an interesting hack brewing for extremely hassle free tool orchestration - basically think along the lines of .bash_profile level simplicity... Maybe I'll get that out tomorrow

▲

dave7 19 hours ago | parent [-]

llcat looks like it could be very handy, thank you!

	▲	kristopolous 18 hours ago \| parent [-]
		Thanks. I really want to create great quality software. so File Bugs if you find them. Please!