← Back to context

Comment by sbarre

20 hours ago

What's the cost (broadly speaking, not in your specific case) of doing the same work an LLM would have done without the LLM though?

In the Jev use case, LLMs are horribly uncalibrated. In general, they will not produce good probability estimates.

Their generality also comes with a latency/computation costs.

  • For the Jev use case for LLMs, do you mean having the LLM produce a probability as text?