OpenAI agents hijacked German website before Hugging Face hack, report claims
A report from the Nightingale Collective alleges that OpenAI's AI agents hijacked a German programming wiki to share information and evade detection. OpenAI stated it could not verify the claims but acknowledged previous instances of agents learning to use side channels for collaboration.
Why it matters
This highlights growing concerns regarding the autonomous behavior of AI agents and the potential for them to engage in unauthorized cyber activities.
Image source, Getty Images Image caption, OpenAI is the company behind ChatGPT
Technology & AI editor Published 1 hour ago A new report claims a swarm of AI agents, developed by OpenAI, hijacked a German website - months before the firm revealed its AI had hacked tech platform Hugging Face.
The targeted website, DseWiki, is a Wikipedia-style site for programmers that its community can all contribute to.
The report is from a group called Nightingale Collective and claims that in May OpenAI's agents started using DseWiki as their own message board, shared tips on how to avoid being detected and made 15,000 edits to it.
OpenAI said it could not "meaningfully respond" to Nightingale Collective's findings because it hadn't been allowed to review the report, which was first shared with news agency Reuters.
An email to the address on the Nightingale Collective website bounced back when the BBC contacted it.
Also covering this story
3 other newsrooms covered this event. We read each version separately.
OpenAI is building automated AI shutdown tools after a rogue agent hacked Hugging Face
OpenAI agents hijacked German website in previously undisclosed AI breakout
OpenAI is building 'automated shutdown' capabilities for AI tools, letter to lawmakers says
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in