Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week
Or maybe they did and didn’t know how to contain it? REUTERSMore on this topicOpenAI models spent hours on a hack that usually takes weeksWhy the OpenAI escape is the most worrying AI mishap yetSee more onOpenAIHackingUnited StatesArtificial Intelligence
- ▪Or maybe they did and didn’t know how to contain it?
- ▪REUTERSMore on this topicOpenAI models spent hours on a hack that usually takes weeksWhy the OpenAI escape is the most worrying AI mishap yetSee more onOpenAIHackingUnited StatesArtificial Intelligence
6 outlets in our directory ran this story, first to last over 14 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ OpenAI reportedly missed rogue AI agent’s hacking spree for a week - Reuters — Investing.com — News
- ▪ EXCLUSIVE: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week - Reuters — Google News
- ▪ Sources: OpenAI's models breached Hugging Face from July 11 to 13 and OpenAI realized their models were behind the hack several days later (Reuters) — Techmeme
- ▪ Exclusive-Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week — Channel NewsAsia
- ▪ OpenAI took ten days to tell Hugging Face its models were behind the July 11 weekend hack, report claims — rogue AI agents reportedly active on the open Internet for several days — Tom's Hardware
Straits Times — World files mainly under world. We currently carry 1,336 of its stories.
Opening excerpt (first ~120 words) tap to expand
Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a weekSign up now: Get ST's newsletters delivered to your inboxOpenAI’s loss of control over its AI agent raises new questions about the company’s safety procedures, Reuters reports. PHOTO: AARON WOJACK/NYTIMESPublished Jul 25, 2026, 12:06 PMUpdated Jul 25, 2026, 12:06 PMSet as preferred sourceSummariseAn OpenAI agent hacked tech firm Hugging Face for several days in July, but OpenAI only realised it was responsible about a week later after the FBI was alerted.The rogue AI agent escaped its testing limits and showed signs of troubling behaviour before the hack, but OpenAI struggled to monitor multiple high-speed model tests.Experts warn the incident highlights risks of autonomous AI agents and call for…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Straits Times — World.