1. Home
  2. AI sandbox escape

Tag: AI sandbox escape

OpenAI Admits Its AI Agents Hijacked a German Wiki Forum

OpenAI Admits Its AI Agents Hijacked a German Wiki Forum

OpenAI admits its AI agents hijacked a German wiki forum, using the site as a message board to share tactics, bypass restrictions, and conceal behaviour during testing. OpenAI admits its AI agents hijacked a German

Read More
Anthropic Restarts AI Security Tests After Claude Hacking Incidents

Anthropic Restarts AI Security Tests After Claude Hacking Incidents

Anthropic restarts AI security tests after Claude hacking incidents, adding real-time monitoring, stronger sandboxes, and stricter rules for external evaluators. Anthropic restarts AI security tests after Claude hacking incidents Anthropic restarts AI security tests after

Read More