1
Ask HN: How are thinking efforts implemented?
Claude与ChatGPT的"思考投入"机制是独立模型还是同参数不同效果？作者通过缓存行为差异切入，探讨大模型推理能力的实现方式。
Claude and ChatGPT have thinking efforts where you can tune the amount of thinking allowed. Like low, medium, high, xhigh and so on. But are they diff…