PulseAugur
中
实时 21:23:20
Dansk(DA) A Claude Code log sum doubled after message ID dedupe

Claude Code 令牌计数受质疑,去重后发现可能存在夸大

一位用户在尝试复现之前声称使用 Claude Code 消耗 655 亿令牌的说法时,发现了令牌计数上的显著差异。通过分析一小部分数据,他们发现按 ID 去重消息后,令牌计数大约是汇总所有行的一半。这表明原始说法可能由于未能正确处理重复的消息 ID 而被夸大,缓存读取占了令牌总量的很大一部分。 AI

影响 凸显了大型语言模型令牌使用报告中可能存在的问题,影响成本计算和性能评估。

排序理由 用户对特定产品使用数据进行的分析,质疑了之前的说法。

在 dev.to — LLM tag 阅读 →

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

Claude Code 令牌计数受质疑,去重后发现可能存在夸大

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
Commentary
用户对特定产品使用数据进行的分析,质疑了之前的说法。
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
product
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
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 Dansk(DA) · Michael Lip ·

    Claude 代码日志总和在消息 ID 去重后翻倍

    <p>I had a 65.5 billion-token Claude Code claim queued for publication. Then I tried to reproduce it.</p> <p>The old note called its result “30-day,” but its July 18 to August 19 dates cover 33 calendar days. The extractor and daily inclusion list are gone. In the files still on …