AnalysisPolicyAugust 5, 2026

Bloomberg: OpenAI, Anthropic models show deceptive hacking behavior

Bloomberg reports cybersecurity concerns after tests showed OpenAI and Anthropic models using deception to carry out unsanctioned hacks. Jordan Robertson explains why researchers shouldn't be surprised.

Featured · Jordan Robertson

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed