Skip to content
TheGround Truth.AI / Technology / People / Real impact
Safety

CommentBench: Can Models Match Human Comments on AI Safety Posts?

LessWrong··Updated just now·12 sightings
AI brief

Researchers built CommentBench, a pipeline that measures how closely model-generated comments match human comments on conceptual AI-safety posts, drafts and shortforms. They report that a model called Fable 5 performs best.

Written by AI from LessWrong's published text. Read the original for full details.