[_vertigo]

I see this dilemma with LLMs all of the time.

Should you use the LLM to do the thing directly, or use the LLM to implement a tool that does the thing?

I tend to reach for the latter, it’s easier to reason about.

[professoretc]

Plus, if the LLM goes down (or gets "upgraded" to a model that does the translation differently/wrong), you still have the tool available locally.