Attention Is Not What You Need (2025)(arxiv.org)
177 points by westurner | 62 comments
arXiv paper proposing an attention-free sequence model using Grassmann flows and Plucker coordinates, compared against Transformers on Wikitext-2 and SNLI.
#language-modeling on Hacker News
2 stories tagged language-modeling, newest first.
Compression is prediction(ngrok.com)
611 points by nikolay | 252 comments
An ngrok blog post explaining compression basics and how data compressors and LLMs fundamentally solve the same prediction problem.