Tinker lead: DeepSeek models strong but less popular for post-training than Kimi

cHHillee · x · 2026-09-27

cHHillee (Thinking Machines) says model selection ranks fairly low on Tinker's improvement list, and asks what people actually want to post-train. Anecdotally, DeepSeek models — long strong and popular — seem less chosen for post-training than Kimi. He also acknowledges Tinker still has significant scaling work ahead.

Original post →

More from Models

Models channel →