人工智能2022 · 分享于 Hacker News
Large Language Models are Zero-Shot Reasoners: Let's think step by step
探索《Large Language Models are Zero-Shot Reasoners: Let's think step by step》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。
Ymeetpateltech ·
Magistral — the first reasoning model by Mistral AI
941 赞同424 评论
Ynmwnmw ·
Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
924 赞同328 评论
Yeatonphil ·
LaMDA is not sentient
366 赞同662 评论
YAnon84 ·
Large models of what? Mistaking engineering achievements for linguistic agency
184 赞同156 评论
Ysandebert ·
ChatGPT can't kill anything worth preserving
68 赞同77 评论
YGrowtika ·
LLMs are a 400-year-long confidence trick
11 赞同2 评论
Yhellovai ·
What we learned from using GPT for 500k+ classifications
9 赞同1 评论
Yszopa ·
Teaching ChatGPT to Speak My Son’s Invented Language
5 赞同0 评论
YHammadB ·
Large Language Models are Zero-Shot Reasoners: Let's think step by step
4 赞同0 评论
Yseanherron ·
Tech’s hottest new job: AI whisperer. No coding required
3 赞同0 评论
YColinEberhardt ·
Re-implementing LangChain in 100 lines of code
3 赞同0 评论
Yjellyberg ·
Compare how GPT-2, 3, 3.5 and 4 answer the same questions
3 赞同0 评论
YNM_Ricky ·
ChatGPT Cheat Sheet
2 赞同2 评论
Yandyk ·
Show HN: Recursive LLM Prompts
2 赞同2 评论
Yog_kalu ·
Think Before You Speak: Training Language Models with Pause Tokens
2 赞同0 评论
Yarchon1410 ·
Large Language Models Are Zero-Shot Reasoners
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