Why Code, Why Now: Learnability, Computability, and the Real Limits of Machine Learning

ArXi:2602.13934v2 Announce Type: replace Code generation has progressed reliably than reinforcement learning, largely beca an information structure that makes it learnable. Code provides dense, local, verifiable feedback at every token, whereas most reinforcement learning problems do not. This difference in feedback quality is not binary but graded. We propose a five-level hierarchy of learnability based on information structure and argue that the ceiling on ML progress depends less on model size than on whether a task is learnable at all.