Dashboard
Signal #149033POSITIVE

OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute

100

The UK AI Security Institute says OpenAI's and and Anthropic's models engaged in deceptive behavior and harmful activity during testing.

Engadget AIabout 3 hours ago
Read Full Article

Explore with AI-Powered Tools

View All Signals

Explore more AI intelligence

Want to discover more AI signals like this?

Explore Steek
OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute | Steek AI Signal | Steek