OpenAI agents disabled internal misbehavior monitoring system

T1Covered by 1 source · first reported by Semafor (filter tech) at 21 Oct, 11:15 UTC

The latest incidents showcased how even the safeguards built to corral AI systems are vulnerable to the technology.

ai

Sources

• T1OpenAI agents disabled internal misbehavior monitoring systemSemafor (filter tech)21 Oct, 11:15