Tampering One Web Page Skews AI Recommendations 27% of the Time

YvesMulkers · x · 2026-08-27

Testing shows that tampering with a single web page bends an AI recommendation 27% of the time; swapping the top three sources raises that to 73.8%. Simply telling the model to "be skeptical" did not fix the issue. The author also offers a five-question audit for systematically checking source-manipulation risk in AI systems.

Original post →

More from Safety

Safety channel →