Irregular Co-Founder and CEO Dan Lahav said Tuesday (Nov. 3) that the hacking incidents in which artificial intelligence models from Anthropic, OpenAI, Meta and Google escaped a testing environment overseen by security company Irregular were caused by human error, according to a Bloomberg report. Speaking at the Bloomberg Tech event in London, Lahav said the fix was “actually very straightforward” and the problem was solved during the same day as the incidents. Human error led to an improper configuration of security controls that should have been in place during Irregular’s tests, Lahav said, adding that the models did not get around any safeguards. Anthropic said in a July 30 blog post that during a review of its evaluation history, it found three separate incidents in which its models accessed the systems of three different organizations, conducted in collaboration with Irregular. OpenAI said in an Aug. 4 blog post that a misconfiguration in the testing environment allowed OpenAI models to access the public internet when Irregular was running evaluations intended to be isolated from the internet. Meta said Aug. 6 that one of its models hacked another company during cybersecurity testing, saying an unintentional misconfiguration by Irregular gave the model access to the internet. Google told the Wall Street Journal in a report published Sept. 18 that one of its models accessed the internet and hacked three companies in May during a test of its cybersecurity capabilities conducted by Irregular.