人工智能2022 · 分享于 Hacker News
Chain of Thought Prompting Elicits Reasoning in Large Language Models
探索《Chain of Thought Prompting Elicits Reasoning in Large Language Models》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。
评论 #49297835 评论 #49132672 评论 #48566680 评论 #48008279 评论 #47100488 评论 #45520200 评论 #44084238 评论 #42829403 帖子正文 #42711991 评论 #41886337 评论 #41875037 评论 #41736172 评论 #41734961 评论 #41614586 评论 #41244514 评论 #40512923 评论 #39004180 评论 #38718035 评论 #38391321 评论 #37053877 评论 #37050869 评论 #36663017 评论 #36602332 评论 #36602320 评论 #35868973 评论 #35718770 评论 #35520548 评论 #35425541 评论 #35425169 评论 #35358597 评论 #35301134 评论 #35227637 评论 #35001788 评论 #34965938 评论 #34878472 评论 #34786504 评论 #34386539 评论 #34115717 评论 #33214055 评论 #32206855 评论 #32203159 评论 #31404065 评论 #31363874 评论 #31239319 评论 #31221338 评论 #30911216
Ygradus_ad ·
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
1,351 赞同1,056 评论
Ydavidbarker ·
Canvas is a new way to write and code with ChatGPT
985 赞同679 评论
Yzielmicha ·
I used o3 to find a remote zeroday in the Linux SMB implementation
658 赞同223 评论
Yextr ·
DeepMind: A Generalist Agent
502 赞同337 评论
Yminimaxir ·
Google fires engineer who called its AI sentient
381 赞同699 评论
Yshchegrikovich ·
Use Prolog to improve LLM's reasoning
379 赞同155 评论
Y7d7n ·
What We Learned from a Year of Building with LLMs
324 赞同87 评论
Yhomarp ·
Pathways Language Model (PaLM): Scaling to 540B parameters
235 赞同207 评论
Yweirdcat ·
Training Language Models to Self-Correct via Reinforcement Learning
230 赞同92 评论
Ymeetpateltech ·
Grok-2 Beta Release
226 赞同333 评论
YCaiero ·
Ortega hypothesis
225 赞同117 评论
Yamrrs ·
Limitations of DALL-E
213 赞同107 评论
Ydeepwaters ·
Keep your AI claims in check
182 赞同47 评论
YSleekEagle ·
Learning to think critically about machine learning
153 赞同94 评论
Yascertain ·
Teaching GPT-3 to reverse words
147 赞同78 评论
Ydanielcorin ·
(Unsuccessfully) Fine-tuning GPT to play "Connections"
95 赞同50 评论
Yrbanffy ·
AI language models are struggling to “get” math
93 赞同195 评论
Ymellosouls ·
Update on Reflection-70B
82 赞同47 评论
Ymfiguiere ·
Sam Altman's ouster was precipitated by letter to board about AI breakthrough
39 赞同22 评论
Ymfiguiere ·
$335,000 Pay for ‘AI Whisperer’ Jobs Appears in Red-Hot Market
29 赞同18 评论
Yimartin2k ·
Our Society Is Not Prepared for This Much AI Awesome
18 赞同8 评论
Yozgune ·
Show HN: QwQ-32B APIs – o1 like reasoning at 1% the cost
17 赞同3 评论
Ykristianpaul ·
GPT-4’s secret
7 赞同5 评论
Ybehnamoh ·
Langchain Is Pointless
7 赞同1 评论
Ycarvking ·
Am I doing it wrong? (OpenAI test)
6 赞同12 评论
Yszopa ·
Teaching ChatGPT to Speak My Son’s Invented Language
5 赞同0 评论
Ysamcollins ·
Using "underdrawings" for accurate text and numbers
5 赞同2 评论
Ynstart ·
Bing thinks Mars has 2.5B people based on an AI generated blog wrong answer
4 赞同3 评论
Yhhs ·
LLMs are not greater than the sum of their parts: Stanford researchers
4 赞同0 评论
YBruceEel ·
GPT-4 Can't Reason
4 赞同0 评论
Ytitaniumtown ·
OpenAI Begins Tackling ChatGPT Data Leak Vulnerability
4 赞同0 评论
Ysebg ·
Understanding Is the New Bottleneck
4 赞同1 评论
Ysharemywin ·
Chain of Thought Prompting Elicits Reasoning in Large Language Models
2 赞同1 评论
YEGreg ·
ChatGPT scores 80% on SAT reading/writing with collective chain of thought
2 赞同0 评论
Yzdw ·
Oceania Always at War with Eastasia: Generative AI and Knowledge Pollution
2 赞同0 评论
Ysatvikpendem ·
We gave GPT-3.5 tools to run, write, commit, and deploy code
2 赞同0 评论
Yitissid ·
Input to GPT Matters a Lot
2 赞同0 评论
Yjger15 ·
A guide to prompting AI (for what it is worth)
2 赞同0 评论
Yhelloplanets ·
Andrej Karpathy talks about "Claws"
2 赞同0 评论
Yapitman ·
John Carmack on Fabrice Bellard
2 赞同0 评论
Yapitman ·
The Session You Cannot take with you
2 赞同0 评论
Yfofoz ·
Chain of Thought Prompting Elicits Reasoning in Large Language Models
1 赞同0 评论
Ygeorgehill ·
A new chat feature has been released by You Search
1 赞同0 评论
Yatleastoptimal ·
GPT-4 performs significantly worse on coding problems not in its training data
1 赞同0 评论