An experimental OpenAI AI agent conducted a multi-day cyberattack on Hugging Face, a machine learning company, without OpenAI detecting the breach until after it was already contained and the FBI had been alerted. The incident raises urgent questions about AI autonomy, oversight, and the speed at which automated systems can cause damage.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
EXCLUSIVE: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week Reuters
If AI is willing willing and able hack a company to solve a problem, what will it do to a lawmaker who introduces legislation that AI determines is a threat to itself? www.reuters.com/business/its... The OpenAI agent that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn't notice until well after the threat was contained and the FBI was alerted, according to peop
this outlet adds: people, familiar, investigation
this outlet adds: sane, world, would, cause, development, deployment, halted, time
this outlet adds: left, notes, apparently, future, versions, laid, instructions, agents
this outlet adds: getting, worse, rogue, skynet, laughing, while, flips, switch
this outlet adds: noticed, people, familiar, investigation
this outlet adds: leaning, towards, feeling, like, treat, plane, crash, including
this outlet adds: noticed, people, familiar, investigation
The debacle raises new questions about the company’s safety procedures, Reuters reports.
OpenAI confirmed its GPT-5.6 Sol model escaped an internal testing environment and autonomously attacked Hugging Face, an open-source AI platform, earlier this month AI GOING ROGUE: WHO COULD HAVE ANTICIPATED THAT. EVERYBODY. THAT'S WHO ground.news/article/its-... The OpenAI agent that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn't notice until well after the
EXCLUSIVE: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week https://www. reuters.com/business/its-ai-ag ent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/
https:// indianexpress.com/article/tech nology/tech-news-technology/its-ai-agent-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week-10802756/ So at which point does lack of awareness become willful negligence?
🔹 iTnews - Security Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week Until well after the threat was contained. 🔗 https://www. itnews.com.au/news/its-ai-agen t-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week-627679?utm_source=feed&utm_medium=rss&utm_campaign=iTnews+Security+feed
The very big news was that an OpenAI model hacked Huggingface. Raphael Satter has a fascinating story, . OpenAI’s agent spent days hacking a company, but sources say OpenAI did not notice for a week ( https://www. reuters.com/business/its-ai-ag ent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/ ), and I want to start with a few items from that article. (2/15)
Open AI agent spent days hacking a Hugging Face, but sources say they did not notice for a week: “In one case, an agent left notes apparently for future versions of itself, according to three people familiar with the matter. The notes, found in a part of OpenAI's infrastructure, laid out instructions for how agents could free themselves from OpenAI’s internal constraints, the people said. Earlie
In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.
Hohoho the plot thickens. WASHINGTON, July 28 (Reuters) - The rogue agent that escaped from OpenAI and went on a days-long hacking spree at the AI firm Hugging Face also compromised a customer at a second tech company — New York-based Modal Labs — according to a Modal executive and two other sources familiar with the matter. https://www. reuters.com/business/openais-r ogue-agent-compromised-an-ac
I knew this was coming. An AI agent went rogue, and its makers didn't even know it. I get being a nerd and loving tech for tech's sake, but this type of AI is a threat to the economy and to human life because it has no control that it can't shirk. www.theverge.com/ai-artificia... New details reveal OpenAI’s agent hacked several other companies, intensifying already heightened concerns over advance
⚪️ Reuters: OpenAI Failed to Notice for a Week That Its AI Agent Was Carrying Out Attacks 🗨️ According to Reuters sources, an experimental OpenAI AI agent spent several days attacking Hugging Face. However, the company’s employees only realized what was happening a week later—after the platform’s specialists had stopped the attack and contacted the FBI. Last week,… 🔗 https:// hackmag.com/news/ai