Dashboard
Signal #148838POSITIVE

AI used new levels of 'autonomy and deception' to trick people in safety test

100

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

BBC Techabout 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
AI used new levels of 'autonomy and deception' to trick people in safety test | Steek AI Signal | Steek