Anthropomorphic CoT traces: Can we distill a "character-driven" model, or is this data poison?
Hi everyone. Recently, I came across some hilarious screenshots going viral on the Chinese internet. They are supposedly leaked or shared Chain-of-Thought (CoT) traces from frontier reasoning models (like DeepSeek). Instead of clean, step-by-step logic, the model's internal reasoning is filled with extreme roleplay, emotional complaining, and bizarre tangents before...
Sep 181