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

Could passing ARC-AGI-(n+1) on release test human-level AI generality?

A post asks how to test human-level generality in AI and quotes a proposed “meta-benchmark”: passing ARC-AGI-(n+1) immediately upon its release.

François CholletFC
Alex NicholAN
2 Sources, 10d ago, first seen 10d ago

TLDR

A post raises the question of how to test human-level generality in AI. It quotes a proposed answer: the ability to pass ARC-AGI-(n+1) as soon as the benchmark is released.

Combined views

36.4K

2 Sources, first seen 10d ago

311 likes46 comments50 saves14 reposts

Combined views

36.4K

2 Sources, first seen 10d ago

311 likes46 comments50 saves14 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Related

The “LLM as a book” case against AI consciousness meets pushback

Josh Albrecht compares fixed LLMs to books; critics say the analogy overlooks implementation and scientific uncertainty.

The backlash risk of “AI killed XYZ” rhetoric

A user argues that AI proponents’ claims about the technology “killing” other things are practically never accurate and shape how people see AI.

Keras community meeting planned for October 2 at 10 a.m. PST

A September 29 invitation says the meeting is open to anyone and will cover the latest developments in the Keras ecosystem.

2 Sources

François Chollet@fcholletWhat is a way to test human-level generality in artificial intelligence? "The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release"10d
Alex Nichol@unixpickle@fchollet But you won't release a benchmark until you make sure it's not saturated--by definition10d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    François Chollet

    2 Sources

    François Chollet@fcholletWhat is a way to test human-level generality in artificial intelligence? "The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release"10d
    Alex Nichol@unixpickle@fchollet But you won't release a benchmark until you make sure it's not saturated--by definition10d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet