Model Suddenly Answers Correctly After Adding 300 Dots

breath_mirror · x · 2026-07-18

A repost highlights an interesting phenomenon: when asking frontier LLMs multi-hop reasoning questions, they usually fail without extra prompts; however, if 300 dots are appended to the prompt, the models "suddenly" get the right answer.

This indicates that model behavior can be highly sensitive to input formatting, implying that prompt details can significantly affect reasoning performance.

Original post →

More from Models

Models channel →