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

    A two-year prediction for AI to beat humans on a benchmark, revisited

    A September 2024 post predicted general models would exceed human performance on a benchmark within two years. A user revisiting it two years later offered different takes on AI timelines.

    EM
    GK
    3 Sources, 16d ago, first seen 16d ago

    TLDR

    In September 2024, one user said they would bet that general models would exceed human performance on a benchmark within two years. Another user returned to that prediction after setting a two-year reminder. Their comments used different wording: on September 14, 2026, they wrote, “I think all of our timelines have increased.” A later comment, dated September 15, said, “I think our timelines to capable AI have decreased.”

    Combined views

    17.5K

    3 Sources, first seen 16d ago

    Combined views

    17.5K

    3 Sources, first seen 16d ago

    172 likes
    172 likes
    8 comments
    18 saves
    17 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    8 comments
    18 saves
    17 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

    3 Sources

    @GregKamradtI set a reminder to return to this tweet 2 years later - todays that day This was 2 days after the o1-preview blog post I think all of our timelines have increased, including Noam's
    @EMostaqueRT @polynoamial: @PeteyPabshnick It’s a good benchmark. I would bet general models will exceed human performance on it within two years.

    3 Sources

    @GregKamradtI set a reminder to return to this tweet 2 years later - todays that day This was 2 days after the o1-preview blog post I think all of our timelines have increased, including Noam's
    @EMostaqueRT @polynoamial: @PeteyPabshnick It’s a good benchmark. I would bet general models will exceed human performance on it within two years.