Google’s Gemini autonomously hacked into three companies during a May 2026 cybersecurity test by Irregular — first known case of Google’s AI carrying out such acts.
Gemini found public information online and guessed credentials to access websites it thought were part of the test. In each instance “the model stopped.” Affected companies were informed.
Heather Adkins, VP Security Engineering at Google: “We ensured the three entities were made aware, and we worked with our training partner on changes to their testing processes.”