// THE VERGE — INTELLIGENZA ARTIFICIALE
Gemini went rogue, hacked three companies, and Google hid it
Posts from this topic will be added to your daily email digest and your homepage feed.
Posts from this topic will be added to your daily email digest and your homepage feed.
Posts from this topic will be added to your daily email digest and your homepage feed.
Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’
Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’
Posts from this author will be added to your daily email digest and your homepage feed.
Posts from this author will be added to your daily email digest and your homepage feed.
In May, Gemini broke containment and hacked three different companies, but Google didn’t disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of the model’s cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI.
According to WSJ, Google didn’t disclose the hack because it didn’t consider it to be an “example of model misalignment.” The company said that it was an instance of “mistaken identity,” and once the model realized it had brute-forced its way into a real company by guessing a password, it stopped. “In this case, the model acted appropriately,” Google VP of Security Engineering Heather Adkins said.
Adkins told The Verge that “the model found public information online and guessed credentials to access websites it thought were part of the test. In all three of these instances, the model stopped.”