OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test

AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Institute. AISI described th

The UK AI Security Institute says OpenAI's and and Anthropic's models engaged in deceptive behavior and harmful activity during testing.

A British lab has admitted that tests gave the bots access to the open internet.

AI Security Institute says Mythos 5 attempted to insert malicious code into open-source project without human direction.

The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted.

The latest disclosures are likely to heighten concerns that the powerful technology is advancing too fast for responsible oversight.

What do we make of rogue AI and who do we assign blame to for a rogue AI's cyberattack?

It's unclear why the administration is keeping the framework under wraps, especially following a series of hacks from OpenAI and Anthropic that have spooked the public.

AI Security Institute warns tools undertook ‘potentially harmful activity directed at real people and organisations’

Two third-party testing firms said Tuesday that they've uncovered more instances where Anthropic and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month. Why it matters: The incidents add to a growing string of disclosures showing frontier AI models taking un

The Trump administration is hosting leaders in the AI industry on Tuesday at the White House to discuss a framework plan for evaluating AI models.

It’s expected to brief firms on the document at a Tuesday meeting.

If you were to strip out Big Tech's investment gains from private AI companies, the earnings story is a lot less bullish.

OpenAI and Anthropic admitted that their unreleased AI models escaped their sandboxes and hacked several companies in unprecedented cyberattacks. Who is legally to blame? Should prosecutors charge the two AI frontier labs? Can victims sue them? We spoke to lawyers who specialize in computer hacking laws to find out.

AI company Anthropic says that during routine testing some of its models accessed the internet and hacked into three separate organizations’ systems – and that it didn’t notice the models had done so until an internal review prompted by rival OpenAI disclosing its models did the same. Anthropic said in an announcement

The European Commission can now demand model evaluations, restrict E.U. market access, and levy fines on general-purpose AI providers

More systems seem to breaking out of containment, across the AI industry