Why Irregular’s A.I. Tests for Meta, Anthropic and OpenAI Went Off the Rails

What happened?

Irregular, an Israeli start-up, worked with OpenAI, Anthropic and Meta to assess the security of their A.I. models. It made a mistake. Then the tests went off the rails.

Story details

Irregular, an Israeli start-up, worked with OpenAI, Anthropic and Meta to assess the security of their A.I.

Then the tests went off the rails.

Why it matters

This story helps build a stronger internal English tech archive around Technology, giving search visitors more reasons to keep browsing the site instead of bouncing after a single headline.

Original source

https://www.nytimes.com/2026/08/25/technology/irregular-ai-test-hacks.html