HN Explorer

nathan-barry

↗ HN profile [ 104 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Can you tell which AI-generated text is watermarked? (watermark-quiz.krishmatta.net)
    1 points 0
  2. 1 points 0
  3. Can gzip be a language model? (nathan.rs)
    15 points 3
  4. Large Text Compression Benchmark (mattmahoney.net)
    3 points 1
  5. Language Modeling Without Neural Networks (nathan.rs)
    2 points 0
  6. Quines in Every Programming Language (Rosetta Code) (rosettacode.org)
    2 points 0
  7. Mercury Edit 2: Fastest next-edit prediction with a diffusion LLM (221ms) (inceptionlabs.ai)
    1 points 0
  8. Noise schedules considered harmful (2024) (sander.ai)
    1 points 0
  9. Show HN: Diffuji – a diffusion-powered instant camera (diffuji.com)
    8 points 5
  10. Generating Shakespeare Without Neural Networks (nathan.rs)
    5 points 0
  11. Recursion and Induction: A Self-Contained Course Using ACL2 (acl2.org)
    2 points 0
  12. Fidenae amphitheatre collapse (27 AD) – 20k dead (en.wikipedia.org)
    2 points 0
  13. Show HN: Tiny Diffusion – Minimal diffusion LM in 364 lines (github.com)

    I previously posted this a month and a half ago: https://news.ycombinator.com/item?id=45876742 I have rewritten it to be much more simple, from 951 lines of code to just 364, with no loss in core functionality or…

    2 points 0
  14. 1 points 0
  15. Anchored Diffusion Language Model (anchored-diffusion-llm.github.io)
    2 points 0
  16. Text Diffusion Models Are Faster at Writing Code (nathan.rs)
    3 points 0
  17. Inside ThunderKittens' Python Bindings (enbao.me)
    2 points 0
  18. Kickstart.nvim: A minimal, single-file starting point for Neovim configuration (github.com)
    1 points 0
  19. How we made AWS Trainium 17x faster (for conv1d) (charleshong3.github.io)
    1 points 0
  20. Show HN: Tiny Diffusion – A character-level text diffusion model from scratch (github.com)

    This is a character-level language diffusion model for text generation. The model is a modified version of Nanochat's GPT implementation and is trained on Tiny Shakespeare! It is only 10.7 million parameters, so you can…

    172 points 12
  21. The Manuscripts of Edsger W. Dijkstra (cs.utexas.edu)
    268 points 23
  22. Streaming DiLoCo: Towards a Distributed Free Lunch (arxiv.org)
    2 points 0
  23. Fast-DLLM: Training-Free Acceleration of Diffusion LLM (arxiv.org)
    70 points 1
  24. BERT is just a single text diffusion step (nathan.rs)
    455 points 17
  25. Rustree: Visualize Rust ASTs in the Browser (rustree.snprajwal.com)
    6 points 1