Chain-of-thought can hurt performance on tasks where thinking makes humans worse (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Chain-of-thought can hurt performance on tasks where thinking makes humans worse

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Investigating how prompt politeness affects LLM accuracy (2025)

Investigating how prompt politeness affects LLM accuracy (2025)(arxiv.org)

132 points by KnuthIsGod 5 months ago | 170 comments

Screenshot of arxiv.org: MemGPT: Towards LLMs as Operating Systems

MemGPT: Towards LLMs as Operating Systems (arxiv.org)

203 points by belter 3 years ago | 105 comments

Screenshot of arxiv.org: Solving a million-step LLM task with zero errors

Solving a million-step LLM task with zero errors (arxiv.org)

200 points by Anon84 11 months ago | 66 comments

Screenshot of arxiv.org: Learning how to think with Meta Chain-of-Thought

Learning how to think with Meta Chain-of-Thought (arxiv.org)

216 points by drcwpl 1 year ago | 56 comments

Screenshot of arxiv.org: Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)

Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)(arxiv.org)

123 points by mkagenius 11 months ago | 33 comments

Screenshot of arxiv.org: Chain-of-Thought Reasoning Without Prompting

Chain-of-Thought Reasoning Without Prompting (arxiv.org)

76 points by og_kalu 2 years ago | 21 comments

Related stories

Screenshot of davidepiffer.com: AI has access to a vastly larger working memory than the human brain

AI has access to a vastly larger working memory than the human brain (davidepiffer.com)

524 points by rzk 2 months ago | 452 comments

A Substack essay by Davide Piffer arguing that AI's edge over mathematicians comes from a vast symbolic working memory rather than superior reasoning.

mathematics working-memory ai-reasoning cognition

Screenshot of news.ucsc.edu: Human brains are preconfigured with instructions for understanding the world

Human brains are preconfigured with instructions for understanding the world (news.ucsc.edu)

414 points by XzetaU8 11 months ago | 284 comments

UC Santa Cruz news article reporting research suggesting early developing human brains are preconfigured with instructions for understanding the world.

neuroscience brain-development brain-organoids uc-santa-cruz

Screenshot of anthropic.com: Reasoning models don't always say what they think

Reasoning models don't always say what they think (anthropic.com)

369 points by meetpateltech 1 year ago | 246 comments

Anthropic research post on whether reasoning models' Chain-of-Thought faithfully reflects their actual reasoning, linking to the accompanying paper.

chain-of-thought reasoning-models ai-alignment anthropic

Screenshot of sciencedirect.com: Loyal workers are selectively and ironically targeted for exploitation

Loyal workers are selectively and ironically targeted for exploitation (sciencedirect.com)

341 points by ck45 3 years ago | 219 comments

Abstract page for a Journal of Experimental Social Psychology paper finding that loyal workers are selectively targeted for exploitation by managers.

workplace-exploitation employee-loyalty social-psychology organizational-behavior

Screenshot of arxiv.org: SkillsBench: Benchmarking how well agent skills work across diverse tasks

SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)

333 points by mustaphah 8 months ago | 142 comments

arXiv paper presenting SkillsBench, a benchmark of 86 tasks across 11 domains measuring whether structured Agent Skills improve LLM agent performance.

llm-agents agent-skills benchmarks skillsbench

Screenshot of jernesto.com: I miss thinking hard

I miss thinking hard (jernesto.com)

1166 points by jernestomg 8 months ago | 633 comments

A personal blog post venting that the author rarely spends days thinking hard about difficult problems anymore, tagged as an opinion piece on AI.

ai-assisted-coding deep-work problem-solving developer-experience