Chuan Jianguo

"Pro Tip for M2 Users: Because M2 relies on Interleaved Thinking, its context is its memory. For best performance, you must retain the full session history, including the thinking steps. We've noticed that much of the community feedback about performance gaps stems from accidentally discarding this vital context, which is a common practice with simpler reasoning models. "

Is this the reason I observe output degradation in subsequent rounds in Chatbox+M2 API? Questions answered correctly in the first turn sometimes become incorrect.