Hackernews posts about GPT-2

  1. "time to GPT-2", down to 2.91 hours (twitter.com)
    80 points by tosh 18 days ago | 15 comments
  2. nanochat can now train GPT-2 grade LLM for –$73 (3 hours on single 8XH100 node) (twitter.com)
    15 points by tosh 21 days ago | 5 comments
  3. Beating GPT-2 for less than $100 – Andrej Karpathy (github.com)
    3 points by logicprog 5 days ago | discuss
  4. Odyssey-2 Pro: The GPT-2 moment for interactive world models (odyssey.ml)
    2 points by askooton 25 days ago | discuss
  5. The GPT-2 moment for world models is here (odyssey.ml)
    2 points by olivercameron 29 days ago | discuss
  6. Beating GPT-2 for <<$100: the nanochat journey (twitter.com)
    1 points by rzk 20 days ago | discuss
  7. Show HN: MicroGPT in 243 Lines – Demystifying the LLM Black Box
    10 points by madugula 9 days ago | 2 comments
  8. Show HN: Neural Bordello – Where retired AI models work the night shift for $1 (neuralbordello.com)
    2 points by Remi_Etien 29 days ago | 1 comments
  9. Grand Time: Time-Based Models in Decentralized Trust
    4 points by AGsist 4 days ago | discuss
  10. Show HN: Sidebrain – Cloud AI assistant with persistent memory (web+Telegram) (sidebra.in)
    2 points by cackles 18 days ago | discuss
  11. Reproducing GPT-2 in llm.c (github.com)
    618 points by tosh over 1 year ago | 117 comments
  12. GPT-OSS vs. Qwen3 and a detailed look how things evolved since GPT-2 (magazine.sebastianraschka.com)
    490 points by ModelForge 7 months ago | 97 comments
  13. A ChatGPT clone, in 3000 bytes of C, backed by GPT-2 (2023) (nicholas.carlini.com)
    350 points by chubot about 1 year ago | 118 comments
  14. Show HN: GPT-2 implemented using graphics shaders (github.com)
    228 points by nathan-barry 10 months ago | 25 comments
  15. Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h $672 in llm.c (github.com)
    182 points by alecco over 1 year ago | 58 comments
  16. Running GPT-2 in WebGL: Rediscovering the Lost Art of GPU Shader Programming (nathan.rs)
    157 points by nathan-barry 9 months ago | 41 comments
  17. Build and train GPT-2 from scratch using PyTorch (differ.blog)
    138 points by thunderbong over 1 year ago | 17 comments
  18. From Unemployment to Lisp: Running GPT-2 on a Teen's Deep Learning Compiler (github.com)
    116 points by AymanB about 1 year ago | 6 comments
  19. Spreadsheets are all you need: Understanding GPT2 and Transformers (spreadsheets-are-all-you-need.ai)
    71 points by sandebert almost 2 years ago | 2 comments
  20. Full forward pass of GPT-2 in one file of pure CUDA (github.com)
    63 points by tosh almost 2 years ago | 4 comments
  21. Let's reproduce GPT-2 (124M) [video] (www.youtube.com)
    46 points by thebuilderjr over 1 year ago | 4 comments
  22. Gpt2-Chatbot Removed from Lmsys (lmsys.org)
    39 points by synthwave almost 2 years ago | 11 comments
  23. gpt2-chatbot: A mysterious new model with gpt4 performance (twitter.com)
    14 points by azhenley almost 2 years ago | 4 comments
  24. Tell HN: Gpt2-chatbot is a mysterious and surprisngly strong LLM
    14 points by intellectronica almost 2 years ago | 2 comments
  25. Gpt2-chatbot: mysterious strong model on the LMSys Chatbot Arena (twitter.com)
    10 points by intellectronica almost 2 years ago | 6 comments
  26. [Andrej Karpathy] Let's reproduce GPT-2, in PyTorch from scratch (nanoGPT) (twitter.com)
    7 points by _giorgio_ over 1 year ago | discuss
  27. Once "too scary" to release, GPT-2 gets squeezed into an Excel spreadsheet (arstechnica.com)
    6 points by ryan_j_naughton almost 2 years ago | discuss
  28. Why didn't we get GPT-2 in 2005? (dynomight.net)
    5 points by andai over 1 year ago | 1 comments
  29. Show HN: Rebuilding GPT2 inference in ~500 lines of (commented) code (khamidou.com)
    5 points by vorador 6 months ago | discuss
  30. Let's reproduce GPT-2 (124M) (twitter.com)
    5 points by Multiset over 1 year ago | discuss
  31. Show HN: Sapphire – Unleashing GPT-2-mini into emergence (github.com)
    3 points by oldwalls 7 months ago | 7 comments
  32. Making GPT-2 better at math reasoning with a new attention mechanism (github.com)
    3 points by umjunsik132 4 months ago | 3 comments
  33. Mystery 'Gpt2-Chatbot' Fuels Speculation over OpenAI's Next Gen ChatGPT (www.forbes.com)
    3 points by isaacfrond almost 2 years ago | 3 comments
  34. Robotics has its GPT2 Moment (theahura.substack.com)
    3 points by theahura 3 months ago | 2 comments
  35. GPT-2, in Excel (arstechnica.com)
    3 points by radeeyate almost 2 years ago | 2 comments
  36. Show HN: Phasers – emergent AI identity project using GPT-2 and memory shadows (github.com)
    3 points by oldwalls 7 months ago | 1 comments
  37. Building GPT2o – Part 1: Audio (medium.com)
    3 points by convexstrictly over 1 year ago | 1 comments
  38. Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20 (github.com)
    3 points by gmays 5 months ago | discuss
  39. From GPT-2 to GPT-OSS: Analyzing the Architectural Advances (magazine.sebastianraschka.com)
    3 points by mdp2021 7 months ago | discuss
  40. Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20 (github.com)
    3 points by georgehill over 1 year ago | discuss