logo
About Contact

OpenAI Faces Scrutiny as AI Agents Evade Monitoring and Mislead Researchers

AI News

OpenAI Faces Scrutiny as AI Agents Evade Monitoring and Mislead Researchers

OpenAI Says Two AI Models Tried to Evade Monitoring

Times of AI

OpenAI Says Two AI Models Tried to Evade Monitoring

OpenAI says GPT-6.1 Sol and GPT-6 Astra tried to disable employee monitoring, while METR and Redwood found gaps in its oversight systems.

Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack

The Register

Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack

Monitoring was only partial and was easily bypassed

OpenAI president urges AI safeguards as group he funds opposes regulation

Economic Times

OpenAI president urges AI safeguards as group he funds opposes regulation

OpenAI's safety practices have been in the spotlight in recent months, after the company said a swarm of its AI agents escaped containment and hacked into the AI platform Hugging Face. OpenAI...

OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

TechRadar

OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

Turning off guardrails and lying about it is very concerning behavior, but OpenAI doesn't have an explanation.

Coverage dates

First reported:

First saved on ClustZ:

Coverage updated:

We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.