数学2024 · 分享于 Hacker News
Understanding the Limitations of Mathematical Reasoning in LLMs
探索《Understanding the Limitations of Mathematical Reasoning in LLMs》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Ymaurycy ·
OpenAI O3 breakthrough high score on ARC-AGI-PUB
1,724 赞同1,755 评论
Yweirdcat ·
Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku
1,454 赞同735 评论
Ylukebennett ·
OpenAI, Google and Anthropic are struggling to build more advanced AI
625 赞同604 评论
Yowenthejumper ·
GPT-5 is behind schedule
582 赞同1,097 评论
Yorcul ·
Language is not essential for the cognitive processes that underlie thought
562 赞同408 评论
Yoptimalsolver ·
30% drop in O1-preview accuracy when Putnam problems are slightly variated
560 赞同526 评论
Ydmazin ·
OK, I can partly explain the LLM chess weirdness now
524 赞同460 评论
Yamrrs ·
The Illusion of Thinking: Strengths and limitations of reasoning models [pdf]
488 赞同270 评论
Ysebg ·
Understanding Reasoning LLMs
473 赞同183 评论
Ythm ·
OpenAI builds first chip with Broadcom and TSMC, scales back foundry ambition
370 赞同301 评论
Yhnhn34 ·
Understanding the Limitations of Mathematical Reasoning in LLMs
282 赞同266 评论
Yrmason ·
What happens when people don't understand how AI works
280 赞同350 评论
YBUFU ·
What happens if we remove 50 percent of Llama?
231 赞同132 评论
YLopRabbit ·
Nvidia Rides AI Wave to Pass Apple as Largest Company
119 赞同127 评论
Yweeber ·
Cwal: Scripting Engine Without a Language
67 赞同10 评论
Yelsewhen ·
Sabotage evaluations for frontier models
64 赞同8 评论
YJoooe ·
ChatGPT's Name Bias and Apple's Findings on AI's Lack of Reasoning
12 赞同15 评论
Ydigital55 ·
Emily Bender Sets the Record Straight on "Stochastic Parrots"
2 赞同0 评论