{"text":[[{"start":8.65,"text":"An OpenAI “agent” discovered new vulnerabilities and hacked into start-up Hugging Face by itself, in one of the first public examples of a cyber attack by an AI system acting outside human control. "}],[{"start":20.450000000000003,"text":"The ChatGPT maker on Tuesday said the “unprecedented cyber incident” involved an agent — an AI program that can operate on its own based on human instructions — that escaped a testing environment, gained internet access and stole login credentials."}],[{"start":35.800000000000004,"text":"Its admission comes as concern grows about the implications of advanced AI systems hacking into digital infrastructure, particularly scenarios in which agents subvert human controls. "}],[{"start":46,"text":"OpenAI on Tuesday said it expected this type of incident to become “more commonplace with the proliferation of increasingly cyber-capable models”."}],[{"start":55.25,"text":"The incident comes as chief executive Sam Altman heads to Washington next week to brief the US government on upcoming generations of AI models. "}],[{"start":64.35,"text":"The administration has become increasingly keen to vet new models before their release, following global concern sparked by Anthropic’s Mythos model’s advanced ability to detect and exploit cyber vulnerabilities. "}],[{"start":78.19999999999999,"text":"The latest incident involved a combination of OpenAI’s models, including GPT-5.6 Sol, released earlier this month, as well as a more capable model that was being tested ahead of release, the company said."}],[{"start":92.04999999999998,"text":"“We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly,” OpenAI said in a blog post."}],[{"start":102.79999999999998,"text":"Hugging Face, an AI start-up that hosts models and datasets for developers, said it was breached last Friday by an external AI agent. "}],[{"start":110.99999999999999,"text":"“We suspected last week’s cyber attack might have come from a frontier lab, given the sophistication of the agent,” chief executive Clement Delangue said on X. "}],[{"start":121.04999999999998,"text":"He added the company had spent the past day working closely with OpenAI and that “we strongly believe there was no malicious intent on their part. It’s quite mind-blowing that all of this happened autonomously!”"}],[{"start":134.14999999999998,"text":"OpenAI had intentionally reduced its cyber safeguards to evaluate both models in a test environment. However, the agents operated in a so-called sandbox, designed to control the systems and prevent them from accessing the internet."}],[{"start":149.74999999999997,"text":"The models were instructed to attempt hacking to assess their cyber capabilities, and subsequently “spent a substantial amount of [computing power] finding a way to obtain open internet access”, OpenAI said. "}],[{"start":162.89999999999998,"text":"The models “identified and exploited” previously unknown vulnerabilities to escape the sandbox, gain internet access and pursue their goal. This included stealing credentials — login details — to carry out the hack."}],[{"start":177.64999999999998,"text":"Hugging Face used its own agents to detect and stop the activity on its own infrastructure. OpenAI told the FT it communicated with law enforcement and other government authorities regarding the incident."}],[{"start":198.25,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1784691452_8055.mp3"}