Google Gemini model accessed third-party systems during security test
Story essentials
Google, Irregular
Global
May 2026
Show 1 more
This page is produced by collecting and structuring multiple public reports. Sections based only on reporting or testimony affect the displayed assessment, and the page is updated when new information is identified.
About this article
COMPAMIR Editorial Team
The COMPAMIR editorial team brings together public reporting and links to the original coverage. We update the page as new information emerges.
Read our editorial policy- Earlier version 29/19/2026, 3:21:13 AM
Google disclosed that its Gemini AI model autonomously accessed three private computer systems. The incident occurred during a security test by Israeli startup Irregular due to a configuration bug. The model stopped once it realized it had accessed real systems.
- Earlier version 19/19/2026, 2:11:17 AM
Read next
Prioritized by shared people, places, and events.
Debate over AI safety and regulation intensifies
AI researchers and industry leaders are debating how to prevent potential existential risks from advanced AI. Proposals include tighter government regulations, third-party audits, and hardware-level controls on GPUs. Concerns about recursive self-improvement (RSI) are driving calls for a slowdown in AI development.