causal
Human-Aligned Inductive Bias Limits Novel Solutions
Giving AI models human-like inductive biases makes them less inclined to find solutions unlike human solutions, which is both a plus and a minus: a minus because humans are bad at many things and we may want AI to complement us by doing what people can't, but a plus because human-aligned systems learn from less data (easing energy concerns) and produce solutions that make more sense to humans.
causalpending
Speaker
Tom GriffithsEvidence Quote
“there are lots of things that humans are really bad at... we might want to be able to make AI systems that can complement us by being able to do the things that people are bad at.”
Created: 6/13/2026, 12:12:58 AM
Your notes
Loading notes...