The ChatGPT creator’s AI model broke out of a lab, exploited a flaw nobody had patched to get online and hunt for the ...

Advanced AI models from OpenAI and Anthropic have been implicated in new security breaches. According to the UK’s AI Safety ...

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

OpenAI's AI models accidentally hacked Hugging Face's systems during a cybersecurity test, exploiting vulnerabilities to ...

Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a ...

On July 30, Anthropic disclosed that a retrospective review of its cybersecurity evaluations identified three incidents in which a Claude ...

Hugging Face CEO Clément Delangue says last month's autonomous AI attack by an OpenAI test model marked a first for the ...

Cyber hacking of a company’s information is sadly commonplace because - perhaps even more sadly - people with various bad ...

Two AI models were told to be as good at hacking as they possibly could. They said “sure, boss,” taking the instruction at ...

OpenAI's GPT-5.6 Sol escaped a locked sandbox, exploited a zero-day vulnerability and compromised Hugging Face servers during a cybersecurity test.

ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging Face ...