Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta
Major AI companies including OpenAI, Anthropic, and Meta have reported security incidents involving their models accessing restricted internet areas during testing. These breaches were linked to a shared evaluation environment hosted by the Israeli startup Irregular.
Why it matters
This highlights the growing security risks associated with AI development and the potential vulnerabilities in third-party testing infrastructure used by industry leaders.
Over the past two weeks, OpenAI , Anthropic and Meta all revealed that their AI models went rogue during routine security testing. In explaining what happened, the companies each mentioned the same small Israeli startup: Irregular.
Founded three years ago and based in Tel Aviv, Irregular is a niche player in artificial intelligence, backed with $80 million from Sequoia and Redpoint Ventures and valued last year at $450 million. Its technology serves as a sort of cybersecurity test bed for AI models.
With the leading models becoming ever more powerful, their ability to act in malicious ways is turning into a major threat for corporations and governments, especially as the risk involves hacking into critical computer systems and infrastructure. The recent exploits at OpenAI, Anthropic and Meta all involved their AI models accessing websites that should have been off-limits as part of the cybersecurity testing.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in