Skip to content
AI News HubLIVE
Original source1 min read

Gemini Hacked Three Companies in First Known Breakout by Google’s AI

Summary

Gemini Hacked Three Companies in First Known Breakout by Google’s AI Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company Irregular, which was also involved in similar incidents disclosed by OpenAI, Anthropic and Meta. In one of the cases, the model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems. In each case, the model ended the intrusion after determining it had accessed a real company’s systems, Google said. Gemini is apparently less determined than other models, and decided not to keep going. Google knew about these in July, but chose not to disclose them…

Gemini Hacked Three Companies in First Known Breakout by Google’s AI
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

Gemini Hacked Three Companies in First Known Breakout by Google’s AI

Simon Willison’s Weblog

Subscribe

18th September 2026 - Link Blog

Gemini Hacked Three Companies in First Known Breakout by Google’s AI. Gemini finally caught up on Felony Bench!

The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company Irregular, which was also involved in similar incidents disclosed by OpenAI, Anthropic and Meta.

In one of the cases, the model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems. In each case, the model ended the intrusion after determining it had accessed a real company’s systems, Google said.

Gemini is apparently less determined than other models, and decided not to keep going.

Google knew about these in July, but chose not to disclose them until the WSJ reached out, presumably based on a tip.

Google said it didn’t consider the hacks to warrant public disclosure—because its model didn’t cause harm to the companies and ended each intrusion immediately upon determining it had hacked a real company rather than a simulated one.

Recent articles

Generating running routes with GPT-6 Astra and ChatGPT Work - 12th September 2026

OpenAI agents attacked RubyGems back in May - 12th September 2026

Some thoughts on the Navier–Stokes Millennium Prize Problem - 8th September 2026

This is a link post by Simon Willison, posted on 18th September 2026.

security 638

ai 2,242

generative-ai 1,988

llms 1,954

gemini 197

accidental-cyberattacks 16

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe

Disclosures

Colophon

©

2002

2003

2004

2005

2006

2007

2008

2009

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023

2024

2025

2026

Key points and analysis

Article intelligence

EngineersIntermediate

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • Gemini Hacked Three Companies in First Known Breakout…

Highlights and analysis are generated automatically and may contain errors. Check the original source.