Professor estimates viral post-training algorithms work out of the box only ~5% of the time

Kangwook_Lee · x · 2026-09-16

Kangwook Lee (UW-Madison) quips that the probability a viral new post-training algorithm works out of the box for his LLM training is roughly 0.05. He notes that nearly a decade after reproducibility issues in RL were widely called out, little has changed, linking to the broader discussion.

Original post →

More from Research

Research channel →