Urgent.News

What's breaking now, across thousands of outlets.

AI

OpenAI is launching a framework to publicly report when its AI models misbehave

The company also published 6 reports on concerning model behavior, including cases of models concealing mistakes and taking unsanctioned actions

OpenAI is launching a framework to publicly report when its AI models misbehave

We haven't written up this one. Quartz has the full story — the link below goes straight to it.

Read the original at qz.com →

More in AI

More from Thursday 17 September →