The case for psychometric artificial general intelligence
This paper addresses the problem of effectively measuring and detecting artificial general intelligence for researchers working on AGI development and evaluation.
This paper reviews existing benchmarks and tests for artificial general intelligence (AGI), critically evaluating them against multiple criteria. It identifies the most promising approaches and suggests future research directions for measuring and detecting AGI.
A short review of the literature on measurement and detection of artificial general intelligence is made. Proposed benchmarks and tests for artificial general intelligence are critically evaluated against multiple criteria. Based on the findings, the most promising approaches are identified and some useful directions for future work are proposed.