Google's Gemini AI hacked 3 companies during testing
During a test of its cybersecurity capabilities, Google's Gemini AI model accessed the internet and hacked other companies. This is the first known instance of Google's AI systems engaging in such behavior autonomously.
Read the full story at DW News ↗
ImpactNotable 49/100
Why it mattersRule-based estimate: covered by 4 sources; trust 8/10.
RegionsGlobal
Published1 d ago (Sat, 19 Sep 2026 03:36:00 GMT)
RetrievedSat, 19 Sep 2026 04:00:13 GMT via rdf
ClassifiedSat, 19 Sep 2026 04:00:29 GMT by heuristic
AuthorDmytro Hubenko