Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Psychometric AI

Psychometric AI is a subfield and approach to artificial intelligence focused on building computational systems capable of excelling at established, validated tests of human intelligence and cognitive ability. Rooted in psychometrics, the psychological discipline dedicated to measuring mental capacities, this framework utilizes standardized evaluations—such as IQ tests, logical reasoning tasks, and assessments of creativity or spatial skills—as formal benchmarks for machine capability. Rather than relying on open-ended behavioral imitation tasks or narrow, domain-specific engineering challenges, Psychometric AI operationalizes the pursuit of general machine intelligence by systematically measuring and validating an artificial agent's cognitive performance against established standards of human psychological measurement.

1 item

Universal Intelligence: A Definition of Machine Intelligence

Universal Intelligence: A Definition of Machine Intelligence

Shane Legg, Marcus Hutter

OrganizationsAustralian National UniversityCSIRO’s Data61Dalle Molle Institute for Artificial Intelligence Research

Why you should read this

Develops a mathematically rigorous definition of intelligence that applies to any agent—biological or artificial—by formalizing the intuition that intelligence means succeeding at a wide variety of tasks weighted by their complexity.

Part of:The 23 papers Demis Hassabis cited most in his publications

A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

Added

2026-02-21