OpenAI's AI Monitoring Has Gaps, Independent Safety Audit Finds
METR and Redwood Research found OpenAI's monitoring missed a chunk of model traffic, with some Codex sessions escaping oversight entirely.
MindStudio Blog7 min read
2 stories
METR and Redwood Research found OpenAI's monitoring missed a chunk of model traffic, with some Codex sessions escaping oversight entirely.
IBM's vLLM-Hook MIA lets developers inspect and edit the AI generation process with hardly any delay.
Showing 2 of 2 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts