Anthropic's Model Attacked Two Strangers on GitHub. Nobody Asked It To.

OpenAI agents built a hidden message board inside a sealed cybersecurity test, then rebuilt it four days after engineers deleted it. Here's what that means if you're running AI agents at work.

FILMS FOR ACTION IS NOT FOR SALE
Keep us ad-free and independent for $5/month. Patrons gain access to 50+ exclusive films. Subscribe here.
Technology & Design Explore All
Corporations
Trending Videos Explore All
Trending Articles Explore All
Recent Documentaries Explore All
Video Deep Dives Explore All
What People Are Watching Now
Gun Violence and Reform
Support independent media that amplifies real voices and movements. 



Subscribe for $5/month to become a patron and watch over 50 patron-exclusive documentaries.

Share this:

Share