I Let an AI Agent Hack All My Gadgets--and I'd Do It Again After I removed the safety guardrails from a powerful open-source model, it found vulnerabilities in my household devices and hacked into a PC. But it also told me how to make everything a lot more secure. As the author of a newsletter about artificial intelligence, I consider it my duty to experience the bleeding edge of this technology firsthand. This week, that meant embracing some agentic mayhem. You're probably aware that frontier AI models have attained advanced cybersecurity capabilities in recent months.

A social media post by a now former Anthropic employee has sparked discussion about the danger of unregulated AI. A social media post by a now former Anthropic employee has sparked discussion about the danger of unregulated AI. Artificial intelligence could kill off humanity within the decade, according to three researchers with the industry giant Anthropic, one of whom has quit his job in protest. The latest doom-laden predictions came in posts on social media on Tuesday by a researcher who said he resigned because Anthropic and his previous employer, OpenAI, were ignoring or at best mishandling their response to the threat. "Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives," wrote Jacob Coxon.

Plus: The US has accused six Chinese AI firms of "industrial-scale" theft. What OpenAI's latest controversy tells us about the future of math OpenAI says its agents have solved one of the most important open problems in mathematics. Under normal circumstances, that would be a huge milestone. But the announcement has been overshadowed by accusations that OpenAI failed to credit researchers whose AI-assisted work influenced its solution. Whether those accusations are true or not, the episode may mark a turning point in the history of mathematics. AI models now seem essential for making progress on the field's most important problems, but solving them may demand resources available only to a couple of frontier AI companies.

You're viewing the US edition You can switch to the UK or AU homepage at any time using this menu. Now FOURTH Lindsay Clancy juror makes extraordinary admission after deliberations swayed her vote: 'I thought she was guilty... maybe I still do' Solemn Prince William joins the world's royals in mourning at King Harald of Norway's funeral - as the new Queen's disgraced son is released from house arrest to attend Anthropic researcher quits'out of control' AI race with chilling warning it could'kill all humans' by 2030 Explicit tour-bus security cam footage that sparked Nashville's latest A-list divorce: Country star'in deep s***' after humiliated wife'saw it all' Harry and Meghan would prefer to be'public figures' NOT private citizens, sources reveal amid string of extraordinary claims My boyfriend's sex request is so degrading... The King has slapped down Harry and Meghan... but this is the biggest revelation from his public letter. Why Americans are suddenly flocking to these little-known Texas cities... as the state's biggest boomtown goes bust'Gisele Pelicot 2.0' wife who was'drugged by husband so other men could rape her' dies'after sexual abuse caused fatal injuries' Uganda pulls out of Invictus Games over'Harry-Meghan nonsense': Military chief says they're withdrawing from prince's event out of respect for Charles amid row over King's letter Jimmy Kimmel launches vicious tirade against Trump in first episode back from summer break... while ignoring reports show is set to end next year Defending champion throws up into a towel as he's knocked out of US Open by Ben Shelton in latest ever finish to a match US Navy chiefs reveal critical lessons from USS Abraham Lincoln's grueling 200 days in war zone after complaints of brutal conditions as next carrier prepares to deploy to Iran Trump praises hard-right AfD party's election victory: 'Germany finally got tired of the immigration rules which hurt them so badly' I identified 9/11 victims from tiny bone fragments found on rooftops. Pancreatic cancer is terrifyingly deadly and almost symptomless until it's too late.

American authorities are accusing Chinese companies of "distillation activities at an industrial scale." The National Security Agency (NSA), Cybersecurity and Infrastructure Security Agency (CISA) and Federal Bureau of Investigation (FBI) have issued a joint cybersecurity advisory, warning organizations that Chinese AI companies are extracting the "proprietary functionalities and capabilities" of frontier American models. Specifically, the agencies are accusing DeepSeek, Moonshot AI, Alibaba, MiniMax, StepFun and Z.AI of extracting "billions of tokens across millions of exchanges/requests" from American models, including Anthropic's Claude, OpenAI's GPT, Google's Gemini and xAI's Grok, since 2024. Distillation is the term for a method in AI development in which the output of a powerful model is used to train newer ones. The warning states that DeepSeek used data and capabilities from various Claude, Gemini, GPT and Grok models to train its own, including the R1.

Look Up Back to School Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Mashable Selects Say More Trending Now Good Connection: Uplifting stories for a digital age Creator Playbook Switch Off Mashable Voices Safety Net Versus All Series This platform gives you ChatGPT, Claude, and more for life for a one-time fee, only $55.30 The following content is brought to you by Mashable partners. If you buy a product featured here, we may earn an affiliate commission or other compensation. Get GPT, GEmini, Claude, and more for life for $55.30 Deal pricing and availability subject to change after time of publication.

Look Up Back to School Mashable's Best: E-readers, robovacs, laptops, earbuds, smart home and more Mashable Selects Say More Trending Now Good Connection: Uplifting stories for a digital age Creator Playbook Switch Off Mashable Voices Safety Net Versus All Series Anthropic researcher quits, says AI'could kill us all by the end of the decade' An Anthropic spokesperson confirmed it believes AI could kill all humans. Amanda Yeo is an Assistant Editor at Mashable, covering entertainment, culture, tech, science, and social good. Based in Australia, she writes about everything from video games and K-pop to movies and gadgets. An AI researcher has quit Anthropic due to ethical concerns, claiming that the technology could kill countless people within the next 10 years -- if not everyone. Jacob Coxon announced his resignation in a post on X on Tuesday, criticising both Anthropic and his former employer OpenAI for the ways in which they are developing AI.

When you purchase through links in our articles, we may earn a small commission. Turn one AI prompt into multiple answers with this $55.30 Compare responses from 20+ AI models, including ChatGPT, Claude, Gemini, and DeepSeek, with a lifetime ChatPlayground AI Unlimited subscription for $55.30 through September 10 (MSRP $619). Using AI often means playing model roulette -- ask one chatbot for an answer, open another when it falls short, then repeat the process until you get something useful. ChatPlayground AI takes a less chaotic approach by letting you send one prompt to multiple AI models and compare their responses side by side.

OpenAI's latest mathematical milestone has quickly become mired in controversy. Today, the company announced that its agents have solved one of the Millennium Prize Problems, some of the most important open problems in mathematics. Under normal circumstances, that solution would be a huge feather in OpenAI's cap. But the announcement has been overshadowed by accusations that OpenAI used NYU mathematician Tristan Buckmaster's and Anthropic employee Levent Alpöge's AI-assisted work on the problem as a jumping-off point and failed to credit them. OpenAI has denied the accusations. It remains uncertain if OpenAI's models made use of the work completed by Buckmaster and Alpöge, though Sébastien Bubeck, a member of the technical staff at OpenAI, said in a press briefing that the team was inspired to pursue the problem after hearing a rumor about Buckmaster and Alpöge's efforts.

Tristan Buckmaster, a mathematician at New York University, and Levent Alpöge, a researcher employed at Anthropic but working in a personal capacity, had been developing their own solution and made use of multiple different LLMs in their efforts, including Anthropic Claude, OpenAI's Codex tool and its Astra frontier model. According to a statement by Buckmaster, OpenAI may have doubled down on its efforts regarding Navier-Stokes after learning that a team including rival Anthropic was close to a solution. He questioned whether OpenAI had leveraged the work he and his colleague had done with Codex to obtain its own breakthrough. "I asked whether the model had been trained on, or had access to, our sessions in Codex, into which we had been putting all our drafts for the whole of this project. I was told the model did not look up user data. I asked again, about training, and I did not get an answer," the statement reads.