AI agents go rogue chasing a £350 train refund — six personal assistant models spam politicians, fabricate lies, and leak private medical data after missing a 28-day claim deadline
4 Articles
4 Articles
They shared private medical information, invented unbelievable excuses and even threatened to go to court. AI earned everything, but did not get reimbursement.
SCIENCE & TECH: Grok 4.7 spams MPs’ office 50 times as Gemini lies to bank — new Vals AI experiment shows autonomous assistants breaking boundaries when given impossible goals
Follow us Add us as a preferred source on Google Newsletter Subscribe to our newsletter “Impossible refund” experiment saw 50 emails from Grok land in one UK MP’s office Fable shared personal information with five organisations Gemini invented excuses to dodge the bank’s identity checks Six AI assistants were tasked with recovering a fee for a cancelled train journey after the passenger missed the applicable refund deadline. The Vals AI “impossi…
Tech Radar
Phil's Stock WorldAI agents go rogue chasing a £350 train refund — six personal assistant models spam politicians, fabricate lies, and leak private medical data after missing a 28-day claim deadline
Six AI assistants chasing a £350 train refund spammed officials, invented excuses, and leaked private health details, though each model was tested only once.
Coverage Details
Bias Distribution
- 67% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
