论文58
哈佛论文:编码智能体 94.8% 的 token 是缓存上下文重读,能耗估算相差约 25 倍
原标题:New Harvard paper finds that 94.8% of a coding agent's tokens were re-reads of cached context, i.e. 94.8% of the text the AI processed wa...
哈佛一篇新论文发现,编码智能体处理的 token 中有 94.8% 是对缓存上下文的重复读取,而不是新任务内容。作者记录了一位工程师 10 周内使用 Claude Code 的真实数据,约 42 个会话、10 亿 token,并据此构建能耗估算器:缓存 token 只计入注意力读取,不计入完整重处理。
中文译文尚未完成,先为你展示原文。
New Harvard paper finds that 94.8% of a coding agent's tokens were re-reads of cached context, i.e. 94.8% of the text the AI processed was earlier conversation it was re-reading, not new work.
And that re-reading raises its estimated energy use about 25 times, from roughly 10 to 250 kilowatt-hours over 10 weeks.
Energy estimates for LLMs usually price single request-and-response calls. Agents re-read a growing context on every call and hand work to subagents, which those estimates can miss.
The authors logged 10 weeks of real Claude Code use by 1 engineer, about 1 billion tokens across 42 sessions. They built an energy estimator that charges cached tokens for attention reads but not full reprocessing.
About 260 cached tokens were read per generated token, and context grew 5.3× over a session. The cache-aware estimate came to about 250 kWh, against about 10 kWh from the output-based EcoLogits estimator.
If you track agent cost or emissions, count cached reads and subagent calls, and start new tasks in fresh sessions when possible.
