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.
Technology
A.I. Is Becoming So Powerful, It’s Stumping Those Trying to Contain It
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.
Sheera Frenkel
August 25, 2026
1 min read
0 views
Share this article
Related Articles
Technology1 day ago
Trump Administration’s Blacklisting of Anthropic Was Illegal, Judge Rules
Sheera Frenkel1 min
Technology1 day ago
OpenAI and Other Tech Giants Call for Greater Defense Against A.I. Attacks
Kate Conger1 min
Technology1 day ago
Meta Took Aim at Anthropic. It Is Also One of Its Largest Customers.
Eli Tan and Kalley Huang1 min