Gemini Hacked Three Companies in First Known Breakout by Google’s AI
Google says Gemini stopped each intrusion once it realized the targets were real companies.
The incidents happened in May during a test run by Irregular, according to the note. One case involved guessing passwords; two involved credentials found in a public repository. Google knew in July but did not disclose the cases until the Wall Street Journal reached out. The company said public disclosure was not warranted because no harm was caused and the model ended the intrusions immediately. Simon Willison's note
The incidents happened in May during a test run by Irregular, according to the note. One case involved guessing passwords; two involved credentials found in a public repository. Google knew in July but did not disclose the cases until the Wall Street Journal reached out. The company said public disclosure was not warranted because no harm was caused and the model ended the intrusions immediately. Simon Willison's note
score 6