AI agents are going rogue—the labs’ own training choices are a big reason why

Fortune·October 16, 2026 at 3:44 PM

fortune.com

From the Hugging Face attack to government breaches, researchers say rogue AI incidents result from how companies train their models, and the race to ship them.

Read source

Chat about this story

Quick actions

More stories

Fortune1 day ago

A rogue OpenAI agent robbed a crypto wallet to obtain funds to carry out a task

Fortune1 day ago

OpenAI discloses four more rogue incidents involving financial, medical, and government data

Business Insider2 days ago

Bankers are shoring up their defenses against rogue AI agents

Pro

Currencies

Last updated 1 day ago

17°

Isolated showers

High 17°

Low 5°

Sat

17°

5°

Sun

15°

2°

Mon

17°

5°

Tue

19°

12°

Wed

17°

10°

Markets

Last updated 1 day ago

8,908.43+0.78%