HackerPapers

arXiv:2510.18212cs.AI

A Definition of AGI

Dan Hendrycks, Dawn Song, Christian Szegedy, Honglak Lee, Yarin Gal, Erik Brynjolfsson, Sharon Li, Andy Zou, Lionel Levine, Bo Han, Jie Fu, Ziwei Liu, Jinwoo Shin, Kimin Lee, Mantas Mazeika, Long Phan, George Ingebretsen, Adam Khoja, Cihang Xie, Olawale Salaudeen, Matthias Hein, Kevin Zhao, Alexander Pan, David Duvenaud, Bo Li, Steve Omohundro, Gabriel Alfour, Max Tegmark, Kevin McGrew, Gary Marcus, Jaan Tallinn, Eric Schmidt, Yoshua Bengio

Abstract

The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.

arXiv comments
Journal reference
DOI
Subjects
cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

Linked by 9 identifiable commenters in 9 comments across 8 threads, from Oct 2025 to Sep 2026. Found in 1 HN submission from Oct 2025 to Oct 2025. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments8 threads

  1. Ask HN: Is September 8th AGI Day? 1 comment

    • > AI, AGI, and intelligence itself are poorly defined. Of course they are. The previous definitions were not credible and nonsensical. > I invite you to add to the literature if you think you have any novel insight, and get it published. That has been already done. You might…

      rvzView on HNParent context

  2. GPT-6 Astra 1 comment

    • I don't think there will ever be universal consensus on....anything. But significant research has been published into its definition, by researchers from the main LLM providers, like https://arxiv.org/abs/2510.18212 Also, I would say SOTA LLM models can sustain a longer, more…

      hereme888View on HNParent context

  3. Study identifies weaknesses in how AI systems are evaluated 1 comment
  4. The Case That A.I. Is Thinking 1 comment

    • Many people who object to the idea that current-generation AI is thinking do so only because they believe AI is not "conscious"... but there is no known law in the universe requiring that intelligence and consciousness must always go together. With apologies to René…

      cs702View on HNParent context

  5. Scientists can't define consciousness, yet we think AI will have it 1 comment

    • It's been an issue for a while, but just a week ago: A definition of AGI https://arxiv.org/html/2510.18212v2 The consciousness will have to wait for another time. But that one's likely to be extremely contentious and more of a philosophy question without practical impact.

      viraptorView on HNParent context

  6. The next chapter of the Microsoft–OpenAI partnership 2 comments

    • That line essentially means 'indefinite support'. This paper was published some days ago that aims to define AGI: https://www.arxiv.org/abs/2510.18212. But crucially, there is no agreed-upon definition of AGI. And I don't think we're close to anything that resembles human…

      InsanityView on HNParent context

    • They are trying. A Definition of AGI - https://arxiv.org/abs/2510.18212 https://news.ycombinator.com/item?id=45713959

      greView on HNParent context

  7. A definition of AGI 1 comment

    • Paper: https://arxiv.org/pdf/2510.18212 That 10-axis radial graph is very interesting. Do others besides this author agree with that representation? The weak points are speed and long-term memory. Those are usually fixable in computing system. Weak long-term memory indicates…

      AnimatsView on HNParent context

  8. What is intelligence? (2024) 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.