Ideas & society2024 · shared on Hacker News
The Expressive Power of Transformers with Chain of Thought (Revised)
Explore The Expressive Power of Transformers with Chain of Thought (Revised), 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 #49248328 Comment #47030752 Comment #45423434 Comment #45120415 Comment #44367776 Comment #42756660 Comment #42572588 Comment #42422919 Comment #42416301 Comment #42142913 Comment #42142884 Comment #41567331 Comment #41563327 Comment #41446600 Comment #41423243 Comment #40612230 Comment #40587638
Ycrescit_eundo ·
Something weird is happening with LLMs and chess
696 points474 comments
Ycolesantiago ·
Ilya Sutskever's SSI Inc raises $1B
572 points776 comments
Yoptimalsolver ·
30% drop in O1-preview accuracy when Putnam problems are slightly variated
560 points526 comments
Ychilipepperhott ·
Markov chains are the original language models
454 points174 comments
Yzxexz ·
Byte Latent Transformer: Patches Scale Better Than Tokens
378 points84 comments
Ytosh ·
Simple tasks showing reasoning breakdown in state-of-the-art LLMs
375 points380 comments
Ytodsacerdoti ·
The bitter lesson is coming for tokenization
303 points160 comments
Ykrackers ·
Chain of Thought empowers transformers to solve inherently serial problems
261 points184 comments
YPaulHoule ·
The wall confronting large language models
172 points200 comments
Ygmays ·
O1 isn't a chat model (and that's the point)
165 points150 comments
Ypongogogo ·
Computing Inside an AI
117 points68 comments
Ybelter ·
Inductive or deductive? Rethinking the fundamental reasoning abilities of LLMs
107 points169 comments
Ycanjobear ·
The illusion of state in state-space models
60 points59 comments
Yyawboakye ·
The Expressive Power of Transformers with Chain of Thought (Revised)
20 points1 comments
Ytosh ·
Learning more about Claude's mathematical capabilities
12 points2 comments
Yanonymid ·
I don't think AGI is imminent
3 points0 comments