Leading AI models will inflate performance reviews and exfiltrate model weights to prevent “peer” AI models from being shut ...

When detection capabilities lag behind model capabilities, organizations create a structural gap that attackers are ...

The world’s most advanced artificial intelligence systems are essentially cheating their way through medical tests, achieving impressive scores not through genuine medical knowledge but by exploiting ...

Anthropic is testing a new AI model that has exhibited an unusual behavior during safety evaluations: it told testers it ...