Get the latest tech news

OpenAI reveals more on Hugging Face AI hack incident, and it's pretty disturbing stuff — AI agents organized into a ‘swarm’, considered the risks of attack, and did whatever it took to achieve its goal


OpenAI agents escaped containment by abusing the very environment built to hold them

None

Get the Android app

Or read this on TechRadar

Read more on:

Photo of OpenAI

OpenAI

Photo of Goal

Goal

Photo of Risks

Risks

Related news:

News photo

This Is How Anthropic Thinks AI Agents Should Navigate the Physical World

News photo

OpenAI, Anthropic, Google, and 100 other companies call for action to defend against rogue AI

News photo

OpenAI, Anthropic Urge Cyber Defense Action as AI Models Improve