Sound Research WIKINDX |
![]() |
| Resource type: Miscellaneous Language: en: English Published BibTeX citation key: Hendrycks2025 Email resource to friend View all bibliographic details |
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: 9/9
|
| 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 |
|
"Reading and Writing Ability (RW): Proficiency in consuming and producing written language, from basic decoding to complex comprehension, composition, and usage" (p.2).
Reading and Writing Ability (RW): Captures all of the declarative knowledge and procedural skills a person uses to consume and produce written language.
Added by: Mark Grimshaw-Aagaard
(04/09/2026, 03:11)
|
|
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)
|