OpenAI Enlists METR for Safety Review of Largest RL Run

TLDR — The evaluator will get model snapshots and internal records for a single-run pilot; a broader monitor assessment still awaits agreement on scope....
Signal data─ Neutralconfidence 50%Low materiality
AssetEventsector-trendEvent timeAttention0 readers/hrNormalSmart readers0
The evaluator will get model snapshots and internal records for a single-run pilot; a broader monitor assessment still awaits agreement on scope.... Read the full story at The Defiant
0 impressions · 0 upvotes · 0 comments
Discussion (0)
Reading is open to everyone — posting, replying and reporting need an account.
No comments yet.