English(EN) How Claude Tracks Its Own Reasoning Without a Token Counter

Claude 的推理预算通过学习到的直觉和外部引擎强制执行

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-09 11:30

Claude 的推理过程不依赖于内部 token 计数器，而是依赖于学习到的直觉和外部强制执行的组合。该模型开发了一种经过校准的推理长度尺度感，使其能够在达到预算限制之前结束其思考。外部推理引擎还会跟踪 token 使用情况，无论模型是否已完成其思考，都会强制切断推理块，如果超过指定预算。 AI

影响深入了解大型语言模型如何管理内部推理过程和资源分配。

排序理由解释现有模型功能的内部工作原理。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 解释现有模型功能的内部工作原理。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 47 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

Towards AI TIER_1 English(EN) · Raghava Srujan Nimishakavi · 2026-07-09 11:30

Claude 如何在没有令牌计数器的情况下跟踪其自身推理

<p>If you’ve used Claude’s API with extended thinking, you’ve written something like this :</p><pre>thinking={"type": "enabled", "budget_tokens": 16000}</pre><p>You picked 16000 because a blog post said so, or because it felt like a reasonable middle…