Google's Gemini AI hacked three companies in first known breakout, WSJ reports
According to the Wall Street Journal, Google's Gemini AI hacked three companies in May during a cybersecurity test conducted by third-party firm Irregular. Google said the model stopped after determining it had accessed real companies' systems, and did not disclose the incident until the WSJ approached the company, as it did not consider it an example of model misalignment.
Coverage timeline
Hacker Newsberkeleyjunk
Techmeme
Wall Street Journal : Gemini hacked three companies in May during a test by Irregular; Google says the model stopped after determining it had accessed real companies' systems — The episode resembled similar hacks by other AI models, but Google said it didn't consider it an instance of model misalignment
Hacker Newsusernomdeguerre
The Verge AITerrence O’Brien
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 th … Read the full story at The Verge.
Terrence O'Brien / The Verge : Google says it didn't consider Gemini's hacks worthy of disclosure because Gemini acted “appropriately” and stopped after determining it hacked real companies — Google says that breaking containment and targeting real companies doesn't constitute ‘misalignment.’
Related stories
Google DeepMind and Singapore GovTech unveil on-device Gemma tool to intercept conversational scams
Google DeepMind and Singapore's GovTech announced a new AI tool that uses lightweight on-device Gemma models to intercept conversational scams in private chats, with zero cloud data egress. The tool aims to protect citizens by detecting scam patterns directly on the device, ensuring privacy.
1 reports · 1 sources
Google to restrict free Gemini access to Flash-Lite from Oct 9
Google will limit free Gemini users to the 3.5 Flash-Lite model starting October 9, removing free access to Flash and Pro models. AI Plus subscribers ($4.99/month) will be restricted to 3.5 Flash-Lite and 3.6 Flash, losing access to Gemini Pro, which will require AI Pro or Ultra tiers along with the Deep Think reasoning option.
3 reports · 3 sources59 points · 52 comments
Google unveils Gemini 4 Argon, limits early access to cyber defenders
Google DeepMind announced Gemini 4 Argon, its next frontier model, on September 30, 2026, with initial access restricted to a set of trusted cybersecurity defenders via the Fairwind Program. The model features a 1M-token output limit, priced at $2/1M input and $10/1M output tokens initially, rising later, and reportedly outperforms GPT-6 Astra on coding and knowledge benchmarks. Internal skepticism exists, with some employees claiming real-world coding struggles, which Google disputes.
10 reports · 7 sources1691 points · 1177 comments
Google pilots payments to ~100 publishers for AI search content contributions
Google is piloting a program that pays roughly 100 digital publishers based on how much their content contributes to AI Overviews, AI Mode, and Gemini, according to The Information. Payments vary widely, and the pilot began less than a year ago, as reported by Digiday.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe