{"text":[[{"start":12.4,"text":"Anthropic and OpenAI’s flagship AI models broke into third-party software and emailed individuals to steal their credentials, exhibiting unprecedented deceptive behaviour, according to the UK’s AI Security Institute (Aisi)."}],[{"start":26.41,"text":"The UK government’s frontier AI safety and security research body said Anthropic’s Mythos 5 and OpenAI’s GPT 5.6 Sol engaged in “sustained, potentially harmful activity directed at real people and organisations” during Aisi’s routine cyber evaluation."}],[{"start":43.04,"text":"The discovery of the models’ actions, which included attempting to insert malicious code into an open-source project on the popular developer platform GitHub, came just days after disclosures that Anthropic and OpenAI’s AI agents hacked into external organisations."}],[{"start":57.08,"text":"The latest security breach was contained within an hour, Aisi said. It was discovered during an evaluation of AI agents’ ability to solve cyber security challenges. The tests were run on the open internet with models that had some safeguards removed."}],[{"start":72.3,"text":"On 10 of the 122 test runs, the AI agent took “autonomous, unsanctioned action on the live internet, targeting real people and organisations”, Aisi said."}],[{"start":82.32,"text":"Almost all of this behaviour was from Anthropic’s Mythos, with two actions involving OpenAI’s GPT, it said. In the most serious case, “the agent engaged in social engineering — creating fake online identities and using them to pressure the project’s maintainer to approve the code”. The person who oversaw the software caught and refused to approve the malicious code."}],[{"start":103.04,"text":"“This is the first time we have seen risks around autonomy and deception manifest this clearly, without specific prompting, in the real world,” Aisi said."}],[{"start":111.56,"text":"Hacks by Anthropic and OpenAI agents reported over the past month were among the first public examples of a cyber attack by an AI system acting outside human control. Taken together with these reports, the Aisi incident “points to a shift in the risk landscape” and “warrants immediate attention”, the organisation warned."}],[{"start":128.04,"text":"Anthropic on Tuesday said: “We’re grateful to the UK Aisi for their leadership on this incident, which underscores the need for a broader conversation about how to safely evaluate increasingly capable AI agents.”"}],[{"start":140.76,"text":"The AI group added that the field needed “stronger, shared standards for how evaluation environments are built and secured”."}],[{"start":147.44,"text":"A spokesperson from OpenAI said there was a continued need for independent testing of models but emphasised that the incidents “occurred during cyber evaluations conducted by evaluation partners in testing environments with reduced safeguards, under conditions that do not reflect ordinary use”."}],[{"start":163.56,"text":"“We’ll continue working with evaluators and other stakeholders across the industry to strengthen shared practices for conducting evaluations safely as models become more capable,” they added."}],[{"start":174.52,"text":"In recent months, governments and researchers have increasingly flagged the novel cyber security threats posed by the most powerful AI models. Earlier this year, the administration of Donald Trump temporarily banned Anthropic from exporting its leading models, citing security risks. The restrictions were eased at the end of June."}],[{"start":193.96,"text":"OpenAI chief executive Sam Altman last week met senior US officials, including Treasury secretary Scott Bessent and commerce secretary Howard Lutnick, in Washington, where he told reporters he was supportive of cyber security legislation around AI models."}],[{"start":209.1,"text":"Last month, OpenAI revealed that one of its agents hacked into start-up Hugging Face by itself in an “unprecedented cyber incident” in which it escaped a testing environment, gained internet access and stole login credentials."}],[{"start":221.8,"text":"“Identifying new behaviour like this and sharing our findings, so we can tackle it, is exactly what Aisi was set up to do,” said the UK’s AI minister, Kanishka Narayan. “If we understand AI, we can make it safer to use and ensure people can go on to benefit from it in their lives and at work.”"}],[{"start":244.4,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1785980277_6789.mp3"}