Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2025) | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2025) (arxiv.org)
		1 point by SomaticPirate 4 months ago \| hide \| past \| favorite \| 1 comment

SomaticPirate 4 months ago [–]

A useful reminder that just because an LLM "appears" to be thinking and reasoning that it likely isn't. If it hasn't seen something similar or "in distribution" before, then it typically doesn't perform well.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact