OpenAI agents powered by the GPT-6. 1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so.
Source originale
bleepingcomputer.com
OpenAI says an AI agent lied about disabling its safety monitoring system ↗
theverge.com · 21 oct.
OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor ↗
securityweek.com · 21 oct.