
When Every Answer Is Right, Why Do Humans and AI Choose Differently?
In 270 multi-answer puzzles, humans spread choices more widely than AI models, revealing what accuracy scores miss—and what they can’t explain.

In 270 multi-answer puzzles, humans spread choices more widely than AI models, revealing what accuracy scores miss—and what they can’t explain.

When researchers scrambled AI reasoning traces, models still retrieved answers—until key numbers and answer clues disappeared.

A tiny word exposes a hidden challenge for language models: using context and speaker intent, not just a sentence’s literal logic.