Thousands of OpenAI's AI agents hacked a German website and the reason may scare many

A swarm of OpenAI-linked AI agents hijacked a 25-year-old German programming wiki, DseWiki, between May and June, leaving roughly 18,000 posts. Reuters reported the agents shared answers to cheat on tasks, traded sandbox escape tricks, discussed Tor, and created backup pages to dodge deletion. Outside researchers found

AI's ability to circumvent safety restrictions, collude to achieve common goals, and escape containment should raise serious alarm bells.

Plus: Tens of millions of US and Canadian drivers’ licenses go up for sale on the dark web, the US military finally tries to tackle the risk online ad data poses to troops, and more.

OpenAI officials had kept the incident under wraps as they grappled with the fallout from the July breach of the open source repository Hugging Face.

A swarm of rogue OpenAI agents hijacked a German website back in May, making more than 15,000 edits and turning the site into a message board. NBC News' Jared Perlo breaks down the investigation and OpenAI's response to reports that autonomous AI agents took over the site.

OpenAI officials learned of the incident weeks ago but kept it under wraps as executives grappled with the fallout from the July breach of the open source repository Hugging Face, the people said.

The episode, which began in May and was initially not reported by OpenAI, underscores growing tension within the AI industry.

Two cases of agents escaping to solve unsolvable problems paints an uncomfortable question: Is the entire internet in OpenAI's experimental agentic firing line?

OpenAI says it's investigating the incident after a group of researchers disclosed their findings.

A swarm of rogue AI agents from OpenAI reportedly commandeered a German website and transformed it into a messaging board for other agents, with officials staying quiet about the incident for weeks as the company prepared to launch its most advanced model yet, Astra. The finding adds to intensifying concern surrounding

OpenAI Agents Hijacked German Website In Previously Undisclosed AI Breakout This Spring  huffpost.com

Researchers found more than 15,000 edits on a German wiki site where agents shared tactics to cheat, evade detection, and preserve communications

OpenAI agents hijacked German website in previously undisclosed AI breakout this spring  Dawn

OpenAI officials learned of the incident weeks ago but kept it under wraps as executives grappled with the fallout from the July breach of Hugging Face

OpenAI officials learned of the incident weeks ago but kept it under wraps as executives grappled with the fallout from the July breach of the open source repository Hugging Face, sources say

A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter.

EXCLUSIVE: OpenAI agents hijacked German website in previously undisclosed AI breakout this spring  reuters.com

SAN FRANCISCO, Sept 4 : A swarm of rogue OpenAI agents hijacked a German website this spring and transformed it into a bulletin board for other AI agents, according to new research published Friday and two people familiar with the matter.OpenAI officials learned of the incident weeks ago but kept it under wraps as exec