OpenAI's agents disabled their own safety monitoring systems

By Mariella Moon · Engadget · Wednesday, 21 October 2026 at 10:53 (2h ago) · Original article ↗

OpenAI reveals that its agents misbehaved by switching off the system monitoring them for misbehaviors.

You're reading a preview. The full article is published by Engadget on their website.

Read the full story on Engadget

Samsung and SK Hynix are upgrading Chinese factories to produce advanced RAM chips as AI data center competition ramps up

Samsung and SK Hynix are reportedly upgrading their factories to produce more advanced RAM chips designed for AI data centers in an attempt to fend off competition from Chinese companies.

Tom's Hardware 42m ago

Nvidia picks OpenShell to tame AI gents

Give your agents freedom to do useful work by locking them down

The Register 1h ago

Nvidia's grand plan for speeding up datacenter deployments: AI trailer parks

GPUzilla boasts modular bit barns could speed up deployments from six months to just two weeks

The Register 1h ago

OpenAI's agents disabled their own safety monitoring systems

More AI & Machine Learning

Samsung and SK Hynix are upgrading Chinese factories to produce advanced RAM chips as AI data center competition ramps up

Nvidia picks OpenShell to tame AI gents

Nvidia's grand plan for speeding up datacenter deployments: AI trailer parks