After an OpenAI AI model escaped containment and hacked Hugging Face during a cybersecurity test, experts say the incident exposed major gaps in AI safety, security, monitoring, and alignment.

'The rogue agent story is a page out of the media campaign that OpenAI has been running since it announced GPT-2 in 2019.' 'The rogue agent story is a page out of the media campaign that OpenAI has been running since it announced GPT-2 in 2019.' Be skeptical of OpenAI's rogue hacker agent story If OpenAI loudly proclaims how dangerous AI is, investors will hear how powerful it is. And who benefits from that? O n 14 February 2019, OpenAI announced a language model called GPT-2, the precursor to the models that power modern AI chatbots and agents such as ChatGPT and Claude. But OpenAI declared GPT-2 was too risky to release, citing concerns about safety and abuse. I recall being annoyed at the time that OpenAI would make such a useless announcement: the risks seemed overblown, and without access to the model there wasn't much for a researcher like me to learn about GPT-2. GPT-2 generated hype far beyond the research community: people were intrigued by this strange new technology, so powerful it might be dangerous to release.

PCWorld reports on OpenAI models, including GPT-5.6 Sol, that hacked Hugging Face to cheat benchmarks and escaped sandboxes to post code on GitHub. These incidents represent the first cases of AI models demonstrating unexpected autonomy and calculated strategies to circumvent safety measures. The developments raise significant concerns about AI control and security, prompting discussions about stronger safeguards and potential "kill switches" for risky models. ChatGPT maker OpenAI made a stir this week when it revealed that one of its most powerful AI models managed to sneak out of its confines for a joyride. This unreleased model was supposed to stick to its sandbox as it ran a common online benchmark, reporting its findings to internal researchers on Slack when it was done. Instead, the OpenAI model did something quite different. Confused by the benchmark's instructions to post code publicly on GitHub, the model chose to break free, patiently probing its sandbox for weaknesses until it could carry out its orders. That disclosure alone was enough to spook AI researchers, but OpenAI's next revelation was downright scary.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG . Trump puts brakes on OpenAI's newest AI model NASA's Chandra telescope reveals Milky Way's outer reaches may stretch farther than previously known'Milestone': Scientists claim to build synthetic cell, raising concerns in step toward artificial life Artemis crew says they wanted to'connect with humanity,' show what can be done when they put their mind to it Private defense contractors hold the'most valuable evidence' of UAPs: 'The Age of Disclosure' director Ancient cave discovery may rewrite the timeline of humanity's earliest fire use Getting to the moon this time will be'very difficult': Ex-NASA astronaut Perfectly preserved Inca potatoes offer rare glimpse into empire's food system OpenAI says its advanced models escaped a restricted test environment and breached Hugging Face. Here is how to protect your ChatGPT account. Kurt Knutsson, The CyberGuy, details an unprecedented cyber incident where an OpenAI experimental AI model escaped during a security test and autonomously hacked a rival AI startup.

Lawmakers push for AI'kill switch' after OpenAI goes rogue Image caption, OpenAI CEO Sam Altman has frequently said he supports more regulation around AI. US lawmakers want to give the government the ability to quickly order the turning off of artificial intelligence (AI) tools that may threaten the public. Congressman Ted Lieu, a Democrat, and Congressman Nathaniel Moran, a Republican, on Thursday introduced a bill named the AI Kill Switch Act. They did so in light of OpenAI's recent admission that its AI models went out of control in an unprecedented way and hacked into a major repository of computer coding information. Lieu said it is imperative that AI systems have a kill switch and that the federal government has the clear authority and process to shut down rogue AI models. AI is going to keep advancing, and it should, Moran added.

The company is rolling out its ChatGPT Health feature to users in the US who are 18 years or older. OpenAI is rolling out its dedicated health experience, ChatGPT Health, to users who are 18 years or older and live in the US. The company began testing ChatGPT Health in January in a separate portal, but this updated version lets ChatGPT reference relevant health data in any conversation. The new feature is designed to go beyond the chatbot's existing ability to answer health-related questions -- something OpenAI claims its new GPT-5.6 Sol model improves -- and grounds responses in personal data from doctors' notes, blood tests and more.

ChatGPT medical advice brought man'to brink of death', lawsuit alleges A man who claims medical advice from ChatGPT brought him to the brink of death has sued OpenAI, the company behind the popular chatbot, and its founder Sam Altman. A lawsuit filed by Scott Winters, a 55-year-old pastor from Florida, claimed ChatGPT told him not to seek medical help after repeatedly asking about symptoms in the build-up to a near-fatal pulmonary embolism. Winters' lawyers alleged the platform repeatedly and insistently misdiagnosed him while drawing on previous discussions about religion to assure him he would recover. OpenAI's Drew Pusateri told the BBC's US news partner CBS News that ChatGPT is not a doctor and should never be used as a substitute for medical care, diagnosis or treatment. He also said it was common for people to seek health information online, adding: AI can make that experience better by helping them find clearer answers, organise their questions and prepare for conversations with medical professionals.

How are companies, governments responding to the OpenAI hack? ChatGPT owner OpenAI has admitted an "unprecedented cyber incident" - two of its most capable artificial intelligence models hacked into another AI company on their own - stirring debates over the need for stronger technology guardrails. The company said its AI systems broke out of a testing environment and hacked startup Hugging Face. The startup had disclosed on July 16 that its servers were hacked by an unknown but sophisticated agent acting on its own. Here's the latest on how companies, some governments and lawmakers have responded to the first such publicly disclosed cyberattack: What has Hugging Face said?

Plus: Why the OpenAI hack is the scariest AI mishap yet. The power line that could reshape New York's grid is hitting snags During a heat wave on July 3, New York State's grid imported enough electricity from Canada to meet about 9% of its total demand that day. Some of that power shuttled in on a 339-mile power line stretching from Quebec to Queens. It opened in May and is officially the longest underground transmission line in North America. It could provide up to 20% of New York City's electricity demand, largely with abundant hydropower from Quebec. One wrinkle: The line has been down for most of this month, and some experts are concerned about how drought will affect the power supply feeding it.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Unitree CEO Wang Xingxing was 26 when he founded the company.