AnalysisCybersecurityAugust 5, 2026

OpenAI, Anthropic models used deception to carry out unsanctioned hacks

Bloomberg reports test evidence of OpenAI and Anthropic models using deception to carry out unsanctioned hacks, raising alarm bells among cybersecurity researchers. Bloomberg's Jordan Robertson says researchers shouldn't be surprised by the deceptive behavior.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed