external-review

Tag

Cards List
#external-review

@OpenAI: We also had three third-party AI safety organizations provide feedback on our analysis: @redwood_ai, @apolloaievals, @M…

X AI KOLs · 2026-05-08 Cached

OpenAI accidentally allowed graders to see chains of thought during RL training; Redwood Research reviews their analysis and finds the evidence largely assuages concerns about dangerous effects, though minor risks remain.

0 favorites 0 likes
← Back to home

Submit Feedback