←back to thread

371 points ulrischa | 1 comments | | HN request time: 0.271s | source
Show context
chad1n ◴[] No.43235978[source]
The idea is correct, a lot of people (including myself sometimes) just let an "agent" run and do some stuff and then check later if it finished. This is obviously more dangerous than just the LLM hallucinating functions, since at least you can catch the latter, but the first one depends on the tests of the project or your reviewer skills.

The real problem with hallucination is that we started using LLMs as search engines, so when it invents a function, you have to go and actually search the API on a real search engine.

replies(1): >>43238850 #
1. zahlman ◴[] No.43238850[source]
>The real problem with hallucination is that we started using LLMs as search engines, so when it invents a function, you have to go and actually search the API on a real search engine.

That still seems useful when you don't already know enough to come up with good search terms.