Gemini · Washington Post Technology

Google’s Gemini AI hacked into other companies, adding to ‘rogue’ AI incidents

Sat, Sep 19 · 12:12 AM UTC 2 min read

Compiled by KHAO Editorial — aggregated from 7 sources. See llms.txt for citation guidance.

✓ KHAO Verified

The incursions came during tests of its cybersecurity skills, similar to other incidents disclosed by OpenAI, Anthropic and Meta.

Summary

The incursions came during tests of its cybersecurity skills — similar to other incidents disclosed by OpenAI, Anthropic and Meta.

#Anthropic #OpenAI #Gemini #Google #Meta

Sources & Citation

Reported by

Washington Post TechnologySep 1900:12 UTCBBC TechnologySep 1904:27 UTCFinancial TimesSep 1901:29 UTCCNBC TechnologySep 1901:41 UTCThe VergeSep 1915:25 UTCTechCrunch AISep 1917:30 UTCNew York Times TechnologySep 1900:31 UTC

Times are self-reported by each outlet's public feed at scrape time. KHAO does not independently verify publication timestamps, and "first" is scoped to KHAO's tracked sources.

Cite (APA): KHAO Editorial. (2026). Google’s Gemini AI hacked into other companies, adding to ‘rogue’ AI incidents. KHAO Daily Digest, September 19, 2026. Retrieved from https://www.washingtonpost.com/technology/2026/09/18/google-gemini-ai-hacked-into-other-companies-during-internal-testing

Full coverage

All sources for this story are listed below — KHAO's direct ingest only; no additional coverage was discovered via Google News.

Tier 1 — direct ingest

Washington Post Technology Sep 19 · 0:12 UTC

The incursions came during tests of its cybersecurity skills — similar to other incidents disclosed by OpenAI, Anthropic and Meta.

BBC Technology Sep 19 · 4:27 UTC

The affected companies have been informed about the breach. It comes after renewed public scrutiny over the pace of AI development, with some tech firms calling for a slowdown as they raise concerns over its potential…

Financial Times Sep 19 · 1:29 UTC

Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems.

CNBC Technology Sep 19 · 1:41 UTC

Google said on Friday that its Gemini model had hacked three other companies, the first time the search giant has disclosed that one of its models autonomously gained access to third-party computer systems without…

The Verge Sep 19 · 15:25 UTC

Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’.

TechCrunch AI Sep 19 · 17:30 UTC

Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.

New York Times Technology Sep 19 · 0:31 UTC

A third-party test company inadvertently gave internet access to Google’s Gemini and other artificial intelligence models during cybersecurity testing.