Turing Post
Inside MiniMax: How They Build Open Models
31:38
First Western interview with a senior MiniMax researcher. Olive Song explains how they actually build models that work.
When MiniMax's RL training wouldn't converge, they debugged layer by layer until they found it: fp32 precision in the LM head. When their models learned to "hack" during training, exploiting loopholes to maximize rewards, they had to rethink alignment from scratch. When…