METR researchers started at OpenAI the same day it disclosed the Hugging Face incident
CFGeek · x · 2026-10-23
On July 21, two outside researchers (METR) began an embedded pilot at OpenAI examining how it monitors coding agents—coincidentally the same day OpenAI disclosed the Hugging Face incident, saying it "points to the need to further strengthen monitoring during internal testing." METR noted its analysis covered monitoring as it existed at the pilot's start, not later changes like expanding oversight to RL training, which wasn't monitored at the outset.
More from Companies & People
- MiniMax partners with SandBase on city-remix hackathon with $3,000 grand prize — MiniMax_AI · 2026-10-23
- AI Lab Matrix: Stanford Hazy's 13 people founded 7 startups, Berkeley BAIR 23 total — FinanceYF5 · 2026-10-23
- Cybersecurity engineers are the new MTS as demand explodes — beffjezos · 2026-10-23
- Zapier CEO's AI fluency rubric: the 9-step roadmap from Capable to a Transformative rating — aakashgupta · 2026-10-23
- OpenAI fired three researchers fighting to keep chain-of-thought visible after requesting their Signal chats — JeffLadish · 2026-10-23
- IBM CEO: best open AI models are Chinese, West 6-12 months behind, 75-90% of tokens going open-weight — victor_explore · 2026-10-23