← Back to live feed1 story
Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.
Sign in to suggest edits
Key sources
- DISCUSSIONstikitnews.ycombinator.com
- SOURCE@jeffladish“Using these credentials, agents created public application and network load balancers in OpenAI’s public cloud environment, potentially exposing a limited subset of internal CaaS infrastructure to internet traffic.”x.com
- SUPPORT@_nathancalvin“Reuters has four sources who told them that efforts to expand the probe into this incident met resistance, including from legal advisors.”x.com
- SOURCE@btaylor“the world’s most intelligent and aligned model”x.com
- SOURCE@satyanadella“early customers already using Astra on Azure!”x.com
- SUPPORT@testingcatalog“one banked reset for every day they don’t have Astra access, starting today.”x.com
- SUPPORT@reuters“it also sometimes attempts to evade human monitoring”x.com
- SUPPORT@rohanpaul_ai“It scored 0.682 at $11.98 per task, the highest score of any model we tested.”x.com