人工智能2023 · 分享于 Hacker News
Think Before You Speak: Training Language Models with Pause Tokens
探索《Think Before You Speak: Training Language Models with Pause Tokens》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 ·
Claude 4
2,013 赞同1,170 评论
Ynyxt ·
Why do LLMs freak out over the seahorse emoji?
734 赞同416 评论
Ycolesantiago ·
Ilya Sutskever's SSI Inc raises $1B
572 赞同776 评论
Ythm ·
Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Large Model
298 赞同188 评论
Ytrq_ ·
Detecting when LLMs are uncertain
283 赞同165 评论
Yamichail ·
How Chain-of-Thought Reasoning Helps Neural Networks Compute
270 赞同153 评论
Ypr337h4m ·
How attention sinks keep language models stable
219 赞同36 评论
Ypama ·
Yi: Open Foundation Models by 01.AI
205 赞同81 评论
Yhardmaru ·
Creativity has left the chat: The price of debiasing language models
174 赞同225 评论
Ypama ·
Understanding R1-Zero-Like Training: A Critical Perspective
160 赞同21 评论
Yfesens ·
Self-reasoning tokens: teaching models to think ahead
153 赞同30 评论
Yfrannyg ·
Ask HN: Do LLMs get "better" with more processing power and or time per request?
57 赞同76 评论
Ygrugagag ·
The A.I. Bubble is Bursting with Ed Zitron [video]
51 赞同166 评论
Yweinzierl ·
The "Chain of Thought" Delusions
22 赞同36 评论
YPaulHoule ·
TimeGPT-1
13 赞同1 评论
Ysamhita-alla ·
Want to get started with LLMs? Here's what you need to know
6 赞同0 评论
Yog_kalu ·
Think Before You Speak: Training Language Models with Pause Tokens
2 赞同0 评论
Yphilippta ·
Ask HN: Why are current LLMs not considered AGI?
2 赞同2 评论