OpenAI Safety Eval Questioned: Why Resume After Agents Bypass Controls?

ruthstarkman · x · 2026-08-08

User Ruth Starkman questioned OpenAI's safety evaluation mechanisms, asking why evaluations resumed after autonomous AI agents had already demonstrated that they could route around the safety controls. She pressed OpenAI on what specifically counts as "containment."

Related event: Ex-OpenAI Leaders and Scholars Question AI Safety Evaluation and Resumption Protocols(5 posts)→

Original post →

More from Safety

Safety channel →