Checked for new stories 13m ago

Updates on Irregular

Every AI story we track on Irregular — 3 stories so far, each summarized in our own words and linked back to the publisher that reported it.

Pulled from 123 sources

This month

Cybersecurity5 min read

Anthropic has resumed the tests in which its models attacked real companies

The Next Web
Cybersecurity1 min read

Third-party cyber evaluations involving OpenAI models

Simon Willison's Weblog
Cybersecurity16 min read

Investigating three real-world incidents in our cybersecurity evaluations

Covered by 14 sources
That's everything we have on Irregular right now