Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper critiques the field of AI's reliance on behavioral evaluation, arguing it mirrors behaviorism in psychology and limits our understanding of true intelligence. It claims that focusing solely on indistinguishable outputs, as proposed by Turing, prevents the field from investigating the underlying computational processes and mechanisms that differentiate intelligent systems. The authors advocate for a cognitive revolution in AI evaluation, urging a shift towards incorporating methods from cognitive psychology and neuroscience to assess internal organization and processes, rather than solely relying on behavioral outputs.
AI's obsession with behavioral benchmarks is blinding us to the crucial differences in how machines and humans actually *think*, hindering progress towards genuine intelligence.
In 1950, Alan Turing proposed replacing the question"Can machines think?"with a behavioral test: if a machine's outputs are indistinguishable from those of a thinking being, the question of whether it truly thinks can be set aside. This paper argues that Turing's move was not only a pragmatic simplification but also an epistemological commitment, a decision about what kind of evidence counts as relevant to intelligence attribution, and that this commitment has quietly constrained AI research for seven decades. We trace how Turing's behavioral epistemology became embedded in the field's evaluative infrastructure, rendering unaskable a class of questions about process, mechanism, and internal organization that cognitive psychology, neuroscience, and related disciplines learned to ask. We draw a structural parallel to the behaviorist-to-cognitivist transition in psychology: just as psychology's commitment to studying only observable behavior prevented it from asking productive questions about internal mental processes until that commitment was abandoned, AI's commitment to behavioral evaluation prevents it from distinguishing between systems that achieve identical outputs through fundamentally different computational processes, a distinction on which intelligence attribution depends. We argue that the field requires an epistemological transition comparable to the cognitive revolution: not an abandonment of behavioral evidence, but a recognition that behavioral evidence alone is insufficient for the construct claims the field wishes to make. We articulate what a post-behaviorist epistemology for AI would involve and identify the specific questions it would make askable that the field currently has no way to ask.