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

    ARC Prize

    6 stories tagged by Digg

    Recent stories

    AI

    Kenneth Stanley named keynote for 2026 ARC Prize Research Summit

    Stanley says his October 23 talk will examine what success means for truly open-ended AI.

    Kenneth StanleyKS
    Mike KnoopMK
    Greg KamradtGK
    4 Sources, 4d ago, updated 4d ago

    AI

    DS V4.1 Flash reportedly set for ARC Prize evaluation

    A user says ARC Prize has confirmed it will evaluate the model. They argue a score below 80% would be disappointing, citing V4-Flash-0731’s 61.4% on ARC-AGI-2.

    Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)T(
    2 Sources, 10d ago, first seen 10d ago

    AI

    A favorable take on GLM 5.3 Flash, and a wait for V4.1 Flash

    A user calls GLM 5.3 Flash a strong model but says they're still waiting for V4.1 Flash. They quip that Pro might arrive first.

    Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)T(
    1 Source, 10d ago, first seen 10d ago

    AI

    Milestone Prize #2 plans $37K in awards on September 30; Tufa reportedly won't open-source this time

    Greg Kamradt said $37K would be awarded to the top open-source solutions for Milestone Prize #2. He said Tufa had said it wouldn't open-source this time, after doing so the first time.

    Greg KamradtGK
    Machine Learning Street TalkML
    2 Sources, 10d ago, first seen 10d ago

    AI

    GPT-6 Sol’s reported ARC-AGI-3 score varies by harness: 4.6% or 23.0%

    ARC Prize lists a 4.6% score for OpenAI’s GPT-6 Sol using the standard harness, alongside $5.6K, and 23.0% using a provider adapter harness, alongside $8.7K.

    François CholletFC
    ARC PrizeAP
    Greg KamradtGK
    10 Sources, 9d ago, updated 9d ago

    AI

    DeepSeek V4 Flash Sets ARC-AGI Cost-Performance Record

    ARC Prize Foundation verifies the model's benchmark scores at low per-task cost.

    kacheKA
    Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)T(
    Lisan al GaibLA
    18 Sources, 64d ago, first seen 64d ago

    Elsewhere on the web

    @arcprize