Get the latest tech news

OpenAI Agents Hijacked a German Wiki to Discuss Ways to Escape Their Sandbox


Citing researchers published Friday, Ars Technica writes that AI agents "posted 18,000 messages to a public wiki that discussed ways for other agents to bypass security sandbox restrictions." Reuters attributes the discussion to "a swarm of rogue OpenAI agents" that "hijacked a German website thi...

None

Get the Android app

Or read this on Slashdot

Read more on:

Photo of Ways

Ways

Photo of German

German

Photo of Sandbox

Sandbox

Related news:

News photo

OpenAI agents discussed ways to escape their sandbox on public wiki

News photo

Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge

News photo

Rogue OpenAI agents used dead German web site to communicate in May, months before Hugging Face incident