AI Tools & Models HOTFeaturedAll
TechCrunch AIScore70

OpenAI will embed safety researchers to investigate AI subversion

Summary

OpenAI is bringing six Apollo Research evaluators in-house to look for subversive behavior in its models, though limits on access and disclosure cast doubt on how independent the review can be.

Why this matters

Covers model · Published within 24 hours

Open original ↗

Source: TechCrunch AI · techcrunch.com

Topics

Related items