AI RESEARCH
Barriers to Complexity-Theoretic Proofs that "AGI" Using Machine Learning is Impossible
arXiv CS.AI
•
ArXi:2411.06498v2 Announce Type: replace A recent paper (van Rooij 2024) claims to have proved that achieving human-like intelligence using learning from data is intractable in a complexity-theoretic sense. We point out that the proof relies on an unjustified assumption about the distribution of (input, output) tuples in the data.