Hacker News new | ask | show | jobs
by famouswaffles 932 days ago
I think there is probably some -expected/predicted output, actual output, match- thing going on internally. Like how the brain handles sense data.

Somewhat similar, https://vgel.me/posts/tools-not-needed/ (GPT-3 will ignore tools when it disagrees with them)

1 comments

FWIW this is before OpenAI fine-tuned their models for native function calling and exposed it in the API. Their current models (even 3.5 Turbo) should be much better at this.
The problem in that article wasn't the ability to make the right function calls though. It was that it would make the call, get the result and... potentially ignore the result.