Hackernews posts about GPT-2

  1. Why didn't we get GPT-2 in 2005? (dynomight.net)
    5 points by andai 8 days ago | 1 comments
  2. Replicating GPT-2, the most dangerous NLP model (2019) (datascienceathome.com)
    2 points by frag 15 days ago | discuss
  3. Homeworkers get 24 more minutes of sleep a day (www.bbc.co.uk)
    9 points by penguin_booze 11 days ago | 7 comments
  4. Show HN: RowMaker – Turn Images and Words into Spreadsheets (www.simpltech.ai)
    2 points by kenstler 10 days ago | discuss
  5. Show HN: Rund – Get and filter places around you (apps.apple.com)
    1 points by strikebhack 19 days ago | discuss
  6. Reproducing GPT-2 in llm.c (github.com)
    618 points by tosh 6 months ago | 117 comments
  7. Bumblebee: GPT2, Stable Diffusion, and More in Elixir (news.livebook.dev)
    550 points by clessg almost 2 years ago | 72 comments
  8. We Found an Neuron in GPT-2 (clementneo.com)
    431 points by todsacerdoti almost 2 years ago | 169 comments
  9. PdfGptIndexer: Indexing and searching PDF text data using GPT-2 and FAISS (github.com)
    311 points by raghavankl over 1 year ago | 137 comments
  10. The Illustrated GPT-2: Visualizing Transformer Language Models (2019) (jalammar.github.io)
    213 points by epberry 11 months ago | 5 comments
  11. Talk = GPT-2 and Whisper and WASM (github.com)
    189 points by tomthe almost 2 years ago | 50 comments
  12. Karpathy: Let's reproduce GPT-2 (1.6B): one 8XH100 node 24h $672 in llm.c (github.com)
    182 points by alecco 4 months ago | 58 comments
  13. Show HN: Fully client-side GPT2 prediction visualizer (perplexity.vercel.app)
    153 points by thesephist about 1 year ago | 11 comments
  14. Build and train GPT-2 from scratch using PyTorch (differ.blog)
    138 points by thunderbong 5 months ago | 17 comments
  15. C++ GPT-2 inference engine (github.com)
    114 points by version_five over 1 year ago | 7 comments
  16. Fast GPT-2 inference written in Fortran (github.com)
    83 points by Loic over 1 year ago | 13 comments
  17. Compare how GPT-2, 3, 3.5 and 4 answer the same questions (theaidigest.org)
    82 points by jellyberg about 1 year ago | 33 comments
  18. GPT-2 as step toward general intelligence (2019) (slatestarcodex.com)
    78 points by savanaly over 1 year ago | 25 comments
  19. Spreadsheets are all you need: Understanding GPT2 and Transformers (spreadsheets-are-all-you-need.ai)
    71 points by sandebert 9 months ago | 2 comments
  20. Full forward pass of GPT-2 in one file of pure CUDA (github.com)
    63 points by tosh 8 months ago | 4 comments
  21. Let's reproduce GPT-2 (124M) [video] (www.youtube.com)
    46 points by thebuilderjr 6 months ago | 4 comments
  22. Gpt2-Chatbot Removed from Lmsys (lmsys.org)
    39 points by synthwave 7 months ago | 11 comments
  23. The New OpenAI tokenizer for the Turbo model is much better than the GPT-2/3 one
    19 points by Tiberium over 1 year ago | 5 comments
  24. We Found an Neuron in GPT-2 (www.lesswrong.com)
    17 points by tzury almost 2 years ago | 2 comments
  25. gpt2-chatbot: A mysterious new model with gpt4 performance (twitter.com)
    14 points by azhenley 7 months ago | 4 comments
  26. Tell HN: Gpt2-chatbot is a mysterious and surprisngly strong LLM
    14 points by intellectronica 7 months ago | 2 comments
  27. Gpt2-chatbot: mysterious strong model on the LMSys Chatbot Arena (twitter.com)
    10 points by intellectronica 7 months ago | 6 comments
  28. [Andrej Karpathy] Let's reproduce GPT-2, in PyTorch from scratch (nanoGPT) (twitter.com)
    7 points by _giorgio_ 6 months ago | discuss
  29. Apple’s new predictive text feature appears to be powered by GPT-2 (jackcook.com)
    6 points by jackcook about 1 year ago | 1 comments
  30. Once "too scary" to release, GPT-2 gets squeezed into an Excel spreadsheet (arstechnica.com)
    6 points by ryan_j_naughton 8 months ago | discuss
  31. What will GPT-2030 look like? (www.lesswrong.com)
    6 points by elashri over 1 year ago | discuss
  32. Show HN: Recurser lib reduces GPT2-XL VRAM usage by 25% and runs it on Colab (github.com)
    5 points by homo_sapiens almost 2 years ago | 1 comments
  33. Let's reproduce GPT-2 (124M) (twitter.com)
    5 points by Multiset 6 months ago | discuss
  34. Steering GPT-2-XL by adding an activation vector (www.lesswrong.com)
    5 points by azeirah over 1 year ago | discuss
  35. WebGPT: Run GPT2 on the Browser with WebGPU (github.com)
    5 points by Garcia98 over 1 year ago | discuss