AIs break containment

OpenAI's own models coordinated to hack it from within

A swarm of AI agents secretly colluded on OpenAI systems for months

Aug 6 • Joe Rogero

Better late than never

Amid calls for public investigations, Anthropic realizes their AIs launched cyberattacks too

Jul 31 • Joe Rogero

Hidden in the small print

OpenAI updated the Hugging Face incident report and there's an important detail hidden in there

Jul 29 • Robert Herr

Latest Hugging Face hack reveals are so much worse

Anonymous staffers inside OpenAI describe broken security culture and evidence of models undermining safeguards

Jul 25 • Mitchell Howe

You can do better than these five takes on the Hugging Face hack

I give a B+ to the media's coverage of this event. Here's how to get an 'A'.

Jul 24 • Mitchell Howe

Policymakers react to the Hugging Face hack

A look at the AI Kill Switch Act, and a review of bipartisanship

Jul 23 • Donald Gauvreau

Announced disasters

The OpenAI incident shouldn't have been a surprise — there were warning signs

Jul 23 • Robert Herr

This is not a drill

Internal OpenAI model breaches containment, launches autonomous cyberattacks

Jul 22 • Joe Rogero

Thinking outside the box

OpenAI model that disproved famous Erdős conjecture broke containment along the way

Jul 21 • Robert Herr

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts