[valleyer]

The LLM inference itself doesn't "run code" per se (it's just doing tensor math), and besides, it runs on OpenAI's servers, not your machine.

[chongli]

There still needs to be a harness running on your local machine to spawn the processes in their sandboxes. I consider that "part of the LLM" even if it isn't doing any inference.

[valleyer]

If that part were running sandboxed, then it would be impossible for it to contact the OpenAI servers (to get the LLM's responses), or to spawn an unsandboxed process (for situations where the LLM requests it from the user).