←back to thread

A PM's Guide to AI Agent Architecture

(www.productcurious.com)
205 points umangsehgal93 | 1 comments | | HN request time: 0.2s | source
Show context
barbazoo ◴[] No.45130243[source]
> Confidence calibration: When your agent says it's 60% confident, it should be right about 60% of the time. Not 90%, not 30%. Actual 60%.

With current technology (LLM), how can an agent ever be sure about its confidence?

replies(2): >>45130587 #>>45131981 #
1. esafak ◴[] No.45130587[source]
I was about to say "Using calibrated models", then I found this interesting paper:

Calibrated Language Models Must Hallucinate

https://arxiv.org/abs/2311.14648

https://www.youtube.com/watch?v=cnoOjE_Xj5g