#prompt-engineering

Wiki 3

• Controllable Thinking Style Training-injected markers that toggle the style of a reasoning model's chain-of-thought without changing the answer pipeline
• DeepSeek-V4 Roleplay Thinking-Mode Instructions A Chinese-language guide documenting DeepSeek-V4's training-injected markers that toggle the thinking trace between immersive monologue and pure analysis
• Thinking-Mode Rule Erosion Reasoning modes degrade rule-following — when models "think," they evaluate whether contextual rules are load-bearing and skip the ones they decide are arbitrary