Prover-Verifier Games improve legibility of LLM outputs — HN submission

Sat, 03 Aug 2024 18:05:36 GMT

Prover-Verifier Games improve legibility of LLM outputs

53 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Prover-Verifier Games improve legibility of LLM outputs — mentioned by visarga

Sat, 20 Jul 2024 05:48:13 GMT

> new models will start getting trained with mostly the output of other LLMs That is a naive, flawed way to do it. You need to filter and verify synthetic examples. How? First you empower the LLM, then you judge it. Human in the loop (LLM chat rooms), more tokens (CoT), tool usage (code, search, RAG), other models acting as judges and filters. This problem is similar to scientific publication. Many papers get published, but they need to pass peer review, and lots of them get rejected. Just because someone wrote it into a paper doesn't automatically make it right. Sometimes we have to wait a…

Paper and discussion history. A mention is not an endorsement.

Prover-Verifier Games improve legibility of LLM outputs · HackerPapers discussions

Prover-Verifier Games improve legibility of LLM outputs — HN submission

Prover-Verifier Games improve legibility of LLM outputs — mentioned by visarga