Skip to content
  • Home
  • Journalists
    • Headlines
  • Community
    • Businesses
    • Jobs
    • Learning
    • Marketplace
  • Store
(@)

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

The New York Times – On the Runway:

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
Author: Sheera Frenkel

This post first appeared in The New York Times – On the Runway. Read the original article.

Written by

Sheera Frenkel

in

Anthropic AI LLC, Artificial Intelligence, Computer Security, Computers and the Internet, Cyberattacks and Hackers, Dan Lahav, Hugging Face Inc, Irregular, Meta Platforms Inc, OpenAI Labs, Start-ups, Venture Capital
←CIA Director John Ratcliffe in Moscow for meetings, sources say
“No Notes”: People Are Applauding Glenn Close’s A+ Response To Someone Who Made A Rude Comment About Kim Kardashian→

More posts

  • Barns full of birds from America’s biggest foie gras company just burned down

  • Criterion Channel Acquires Three Shorts By Tomisin Adepeju. The Filmmaker Talks Directing & His Popular Dailies Workshop Series

  • ‘Christina Aguilera: Christmas In Paris’ Producer Vertigo Live Faces Closure Over Unpaid Tax Bill

  • Quentin Tarantino Play ‘The Popinjay Cavalier’ Adds ‘MobLand’ Star Nigel Lindsay & ‘The Crown’s Harry Hadden-Paton To Cast Led By Sacha Baron Cohen

About Us


Support Us

Trademark & Copyright 1998 – 2025 · MOSAEC

  • Facebook
  • Instagram
  • LinkedIn
  • YouTube