Waterloo Study Finds Strong Status Quo Bias in AI Models

University of Waterloo researchers tested 11 AI models with nearly 55,000 prompts and found a strong status quo bias: the models were 7.5x more likely to recommend keeping things unchanged.

2026-10-16 ~ 2026-10-16 · 2 related posts

• LLMs are 7.5x more likely to tell you not to change, finds 55k-prompt study — alex_verem · 2026-10-16
• LLMs are 7.5x more likely to tell you not to change, Waterloo study finds — alex_verem · 2026-10-16