AI & machine learning2024 · shared on Hacker News
Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
Explore Let's Think Dot by Dot: Hidden Computation in Transformer Language Models, 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.
Ymeetpateltech ·
Claude 4
2,013 points1,170 comments
Ygradus_ad ·
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
1,351 points1,056 comments
Ydinkleberg ·
Ask HN: What is your ChatGPT customization prompt?
694 points293 comments
Yahiknsr ·
Helen Keller on her life before self-consciousness (1908)
691 points312 comments
Ythm ·
Tencent's 'Hunyuan-T1'–The First Mamba-Powered Ultra-Large Model
298 points188 comments
Ycscurmudgeon ·
Vision Transformers Need Registers
171 points23 comments
Ypama ·
Understanding R1-Zero-Like Training: A Critical Perspective
160 points21 comments
YJimmc414 ·
Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
159 points32 comments
Yleroman ·
Show HN: Convert HTML DOM to semantic markdown for use in LLMs
146 points56 comments
Ysethkim ·
The End of Moore's Law for AI? Gemini Flash Offers a Warning
113 points75 comments
Yweinzierl ·
The "Chain of Thought" Delusions
22 points36 comments
Ybilsbie ·
Qwen 3.8 27B is excellent, but it defaults to overthinking things
5 points1 comments
Ymustaphah ·
Evaluating AGENTS.md: are they helpful for coding agents?
2 points0 comments
Ytosh ·
Talk like caveman
1 points0 comments