Sound Research WIKINDX

WIKINDX Resources

Hendrycks, D., Song, D., Szegedy, C., Lee, H., Gal, Y., & Brynjolfsson, E., et al. (2025). A definition of AGI.  
Added by: Mark Grimshaw-Aagaard  02/09/2026, 08:06   Last edited by: Mark Grimshaw-Aagaard  06/10/2026, 10:17
Resource type: Miscellaneous
Published
BibTeX citation key: Hendrycks2025
Email resource to friend
View all bibliographic details
 Language: en: English
Categories: AI/Machine Learning
Keywords: Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI
Creators: Alfour, Bengio, Brynjolfsson, Duvenaud, Fu, Gal, Han, Hein, Hendrycks, Ingebretsen, Khoja, Lee, Lee, Levine, Li, Li, Liu, Marcus, Mazeika, McGrew, Omohundro, Pan, Phan, Salaudeen, Schmidt, Shin, Song, Szegedy, Tallinn, Tegmark, Xie, Zhao, Zou		 Views: 16/39
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."
Added by: Mark Grimshaw-Aagaard  
Quotes
     pp. 2–4  
"Reading and Writing Ability (RW): Proficiency in consuming and producing written language, from basic decoding to complex comprehension, composition, and usage" (p.2).

(p.3)

Reading and Writing Ability (RW): Captures all of the declarative knowledge and procedural skills a person uses to consume and produce written language.
• Letter-Word Ability: The ability to recognize letters and decode words.
• Reading Comprehension: The ability to understand connected discourse during reading.
• Writing Ability: The ability to write with clarity of thought, organization, and good sentence structure.
• English Usage Knowledge: Knowledge of writing in the English language with respect to capitalization, punctuation, usage, and spelling. (p.4)

 

  Added by: Mark Grimshaw-Aagaard  04/09/2026, 03:11

Keywords:   Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI
     p. 2  
The definition: "AGI is an AI that can match or exceed the cognitive versatility and proficiency of a well-educated adult."
  Added by: Mark Grimshaw-Aagaard  06/10/2026, 08:18

Keywords:   Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI
     p. 2  
"Decades of psychometric research have yielded a vast battery of tests specifically designed to isolate and measure these distinct cognitive components in individuals. Our framework adapts this methodology for AI evaluation. Instead of relying solely on generalized tasks that might be solved through compensatory strategies, we systematically investigate whether AI systems possess the underlying CHC narrow abilities that humans have. To determine whether an AI has the cognitive versatility and proficiency of a well-educated adult, we test the AI system with the gauntlet of cognitive batteries used to test people. This approach replaces nebulous concepts of intelligence with concrete measurements, resulting in a standardized “AGI Score” (0% to 100%), in which 100% signifies AGI."
  Added by: Mark Grimshaw-Aagaard  06/10/2026, 08:20

Keywords:   Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI
     pp. 51–54, Section appendix i  
Auditory Processing (A)
Weight: 10%
Auditory Processing (A) is the ability to discriminate, remember, reason, and work creatively on auditory stimuli, which may consist of tones and speech units.
We decompose this ability into five areas:
• Phonetic Coding (1%): The ability to hear phonemes distinctly, blend sounds into words, and segment words into parts, sounds, or phonemes.
• Speech Recognition (4%): The ability to transcribe a spoken audio signal into its corresponding sequence of text.
• Voice (3%): The quality and responsiveness of the AI’s synthesized voice.
• Rhythmic Ability (1%): The ability to recognize and maintain a musical beat, including reproducing rhythms, detecting differences between rhythms, and synchronizing by playing or humming along.
• Musical Judgment (1%): The ability to discriminate and judge simple patterns in music.
  Added by: Mark Grimshaw-Aagaard  04/09/2026, 03:45

Keywords:   Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI
     p. 57  
"We do not assume the AGI must be embodied"
  Added by: Mark Grimshaw-Aagaard  06/10/2026, 09:57

Keywords:   Artificial creativity, Artificial General Intelligence, Artificial Intelligence, Definition of AGI, Embodied intelligence, Embodiment
WIKINDX 6.18.0-rc2 | Total resources: 1586 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA) | Time Zone: Europe/Copenhagen (+02:00)