• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Shital Shah Releases TAOCP Open Problems Dataset

    Microsoft engineer posts dataset of unsolved problems from The Art of Computer Programming.

    SS
    1 Source, 26d ago, first seen 26d ago

    TLDR

    Shital Shah, a principal research engineer at Microsoft Research, announced the release of a dataset containing open problems drawn from every volume of Donald Knuth's The Art of Computer Programming. The collection appears on Hugging Face under the name sytelus/taocp_open_problems. Shah stated that frontier AI models should be judged on their ability to solve such problems and that gathering high-quality open problems has therefore become more important.

    Combined views

    1.4K

    1 Source, first seen 26d ago

    Combined views

    1.4K

    1 Source, first seen 26d ago

    13 likes
    13 likes
    4 saves
    2 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    4 saves
    2 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @sytelusI have released a tiny dataset of all open problems from all of the volumes of Knuth's The Art of Computer Programming. I believe the only interesting benchmark for the frontier models moving forward is their ability to solve open problems. This makes collection of high taste open problems more important than ever. For CS, obviously few will come close to Knuth in taste. https://huggingface.co/datasets/sytelus/taocp_open_problems

    1 Source

    @sytelusI have released a tiny dataset of all open problems from all of the volumes of Knuth's The Art of Computer Programming. I believe the only interesting benchmark for the frontier models moving forward is their ability to solve open problems. This makes collection of high taste open problems more important than ever. For CS, obviously few will come close to Knuth in taste. https://huggingface.co/datasets/sytelus/taocp_open_problems