causal
AI generalizes within distribution but cannot transfer
A trained classifier can recognize new instances within the statistical distribution of its training data (a new photo of a dog), but cannot recognize out-of-distribution cases (a cartoon or painting of a dog) or transfer knowledge to a genuinely new domain—so what AI does is not learning in the human sense, since human learning implies using knowledge in novel situations.
causalpending
Speaker
Melanie MitchellEvidence Quote
“what these systems are doing is not learning in the human sense, because we assume that if you've learned something you can use that knowledge in a very new situation. That's still a challenge for AI.”
Created: 6/13/2026, 12:22:42 AM
Your notes
Loading notes...