You can return log probs per token generated. This can be used to asses the conf... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		hyferg on Feb 28, 2023 \| parent \| context \| favorite \| on: Keep your AI claims in check You can return log probs per token generated. This can be used to asses the confidence the model has in handling tasks which involve nominal data. If that’s not helpful, were you getting at having the model return some rich data about the attention weights that went into generating some token?

jsemrau on Feb 28, 2023 [–]

For most of our models we return more information. Especially if you look at it from a vendor/customer perspective I believe this to be quite important.

Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact