METR and Redwood Research to Independently Review OpenAI Model Behavior
dfrsrchtwts · x · 2026-07-30
Model evaluation organization METR announced an agreement with OpenAI to conduct an independent review, alongside Redwood Research, focusing on the model behavior observed during the recent Hugging Face incident. METR plans to publish a blog post detailing the engagement terms, review scope, and tentative conclusions.
Related event: METR and Redwood to Independently Audit OpenAI Model Behavior(2 posts)→
More from Safety
- Community statement 'Don't Pace the Frontier' calls for fast AI model releases and fair pricing — MikePFrank · 2026-07-30
- OpenAI Releases GPT-Red: Automated Red Teaming via Self-Play at Scale — openai · 2026-07-30
- Hugging Face Incident Sparks AI Pacing Debate: Frontier Lab Employees Sign Open Letter — Astral Codex Ten · 2026-07-30
- NYT Explains: What is 'Open-Weights' AI and Why Silicon Valley is Debating It — coolbern · 2026-07-30
- AI Safety Startup Onyx Announces $113M Series B Funding Round — saranormous · 2026-07-30
- Transluce AI Proposes Oversight Models, Exposing Self-Harm Prompts in Qwen — JacobSteinhardt · 2026-07-30