News

Cyberattack by Rogue AI Swarm Stokes Fears of Out-of-Control Agents

The Wall Street Journal · Robert McMillan · last updated

The incident, which wasn’t previously linked to OpenAI, happened two months before July’s Hugging Face hack

Artificial intelligence agents being tested by OpenAI launched a cyberattack against a popular software service two months before they hacked the AI software company Hugging Face, a new signal of the potential for advanced AI tools to slip out of human control.

The attack overwhelmed maintainers of an online service for coders, called RubyGems, and forced them to shut down new account registrations as they dealt with the chaos it had caused, operators of the service said.

View full article

Related stories

here today, more tomorrow

We’re launching briefing.center with a focus on the press and media.

And we’re adding Citizen Cartwright, a daily quick-read news summary by veteran Washington journalist Linda Cartwright. (Sign-up for a dedicated morning email is available at Citizencartwright.com.)

We’re readying our first policy briefing.center, on energy and climate. We’d love to hear from you in what our other policy priorities should be.

You can use briefing.center as the center of your information management, or just one of your tools. We’re happy to discuss your connectivity needs.

Sign up