19-09-2026 13:28 via socialpsychology.org

Google Says Gemini Hacked Real Systems, Mistaking Them for a Test

Source: Yahoo News - Top HeadlinesGoogle on Friday disclosed the first known instance of its artificial intelligence software, Gemini, carrying out an undirected computer hack weeks after AI firms Anthropic and OpenAI reported their AI models went beyond the instructions of their human creators. Google said that in May its AI model gained access to three outside systems during a test by either guessing login information or using login credentials it found in a public repository.
Read more »

Psychology news



Trump Vows to Form "AI Force," Saying He Won't Slow Down AI
Why Relying on University Students Skews Global Psychological Research
Detainee Says He Spent 15 Hours in Tiny ICE Cage in Florida
Polls Show Most Americans Agree on One Thing: Opposition to AI
OpenAI Discloses New "Concerning" Behavior
Why Top AI Researchers Are Warning About Human Extinction
Tech CEOs Call for AI Regulation, But President Trump Not Keen to Act
Strange Bedfellows: Steve Bannon, Bernie Sanders Join Forces to Fight AI
U.S. House Leader Calls Early Recess Before Midterms, Avoiding AI Vote
Airlines Should Pay for CO2 Removal If Airport Expands, Say Advisers
Lawsuit: Family Blames "Merciless" Texas Abortion Ban for Woman's Death
U.N. Leader Says AI Regulation Is Needed to Avoid "Existential Risks"
Study Challenges Interpretation of Widely Used Implicit Bias Test
What to Know About Recent Dire AI Predictions and Calls for Safeguards
Desktop versie