Ideas & society2024 · shared on Hacker News
Byte latent transformer: Patches scale better than tokens (2024)
Explore Byte latent transformer: Patches scale better than tokens (2024), 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 ·
DeepSeek-R1
1,843 points663 comments
Ydiyer22 ·
Show HN: I invented a new generative model and got accepted to ICLR
656 points91 comments
YQuizzical4230 ·
Show HN: I made a website to semantically search ArXiv papers
324 points104 comments
Ytaiboku256 ·
Ask HN: Is anybody building an alternative transformer?
148 points93 comments
Ybelter ·
Tokenisation Is NP-Complete
117 points24 comments
Ydlojudice ·
Byte latent transformer: Patches scale better than tokens (2024)
107 points22 comments
Yphewlink ·
Tokenization for language modeling: BPE vs. Unigram Language Modeling (2020)
80 points39 comments
YMaxLeiter ·
"They're made out of weights"
3 points0 comments
Ymtdewcmu ·
Data Compression Explained
1 points0 comments