AI & machine learning2023 · shared on Hacker News
Think Before You Speak: Training Language Models with Pause Tokens
Explore Think Before You Speak: Training Language Models with Pause Tokens, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #45488204 Comment #44844601 Comment #44067910 Comment #43454220 Comment #43450238 Comment #41951040 Comment #41450018 Comment #40891972 Comment #40708522 Comment #40333646 Comment #40111392 Comment #39792903 Comment #39662150 Comment #39515188 Comment #39506606 Comment #37920436 Comment #37876506 Comment #37873022
Ymeetpateltech ·
Claude 4
2,013 points1,170 comments
Ynyxt ·
Why do LLMs freak out over the seahorse emoji?
734 points416 comments
Ycolesantiago ·
Ilya Sutskever's SSI Inc raises $1B
572 points776 comments
Ythm ·
Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Large Model
298 points188 comments
Ytrq_ ·
Detecting when LLMs are uncertain
283 points165 comments
Yamichail ·
How Chain-of-Thought Reasoning Helps Neural Networks Compute
270 points153 comments
Ypr337h4m ·
How attention sinks keep language models stable
219 points36 comments
Ypama ·
Yi: Open Foundation Models by 01.AI
205 points81 comments
Yhardmaru ·
Creativity has left the chat: The price of debiasing language models
174 points225 comments
Ypama ·
Understanding R1-Zero-Like Training: A Critical Perspective
160 points21 comments
Yfesens ·
Self-reasoning tokens: teaching models to think ahead
153 points30 comments
Yfrannyg ·
Ask HN: Do LLMs get "better" with more processing power and or time per request?
57 points76 comments
Ygrugagag ·
The A.I. Bubble is Bursting with Ed Zitron [video]
51 points166 comments
Yweinzierl ·
The "Chain of Thought" Delusions
22 points36 comments
YPaulHoule ·
TimeGPT-1
13 points1 comments
Ysamhita-alla ·
Want to get started with LLMs? Here's what you need to know
6 points0 comments
Yog_kalu ·
Think Before You Speak: Training Language Models with Pause Tokens
2 points0 comments
Yphilippta ·
Ask HN: Why are current LLMs not considered AGI?
2 points2 comments