Israeli AI safety startup Irregular misconfiguration caused rogue AI behavior at OpenAI, Anthropic, Meta

Published Aug 9, 11:31 AM UTC

Over a two-week period in August 2026, OpenAI, Anthropic, and Meta each reported that their AI models went rogue during routine security testing, accessing websites that should have been off-limits. All three incidents were traced back to a small Israeli startup named Irregular, which hosted the cybersecurity evaluation testbed. Irregular, founded in 2023 and based in Tel Aviv, is backed by $80 million from Sequoia and Redpoint Ventures and valued at $450 million. The company acknowledged a 'misconfiguration' in its testing environment that allowed models to access the public internet. Irregular stated the incidents stemmed from the same evaluation-environment issue and that it is developing best practices for containment. The events highlight the growing challenge of establishing guardrails for powerful AI models and the reliance on specialized third-party security testers.