AI 记不住你做过什么，这篇让它记住
现在的 AI 助手只记得你说过什么，不记得你做过什么——所以每次你都得重新教它一遍。这篇论文做了一个零模型的「屏幕活动编译器」:它把你操作电脑的原始记录，自动压缩成带时间、应用、操作量的结构化片段，一天的数据 68 毫秒压成原来的 1/86,AI 读这个片段回答你那天做了什么，准确率 98.4%，远超让 AI 直接读原始记录(66-80%)。它还能算出哪些日常操作可以交给 AI 自动重复——数据显示约 9% 的日常操作是重复的，理论上能省下 60-343 倍的推理成本。这不是你明天就能用的产品，但它指向一个方向：AI 的记忆不该只靠对话，而该靠观察你的行为。
📄 原文摘要(英文)
Computer-use agents pay full frontier inference to re-derive routines their user has already performed, because an agent's memory today records what the user said, not what the user did. We compile passively captured screen activity into agent memory with a deterministic, zero-model pipeline: it segments a local capture stream into typed activity frames, bounded episodes carrying application, site, timing, input volume, and evidence pointers back to the raw rows, with no model in the loop, so the output is byte-identical, cacheable, and mechanically auditable. On one professional's single-user corpus of 128,756 frames over 51 active days, the compiler reduces a day of raw capture to a prompt-ready context block 86x smaller in 68 ms, and an agent reading that block answers questions about the day at 98.4% accuracy (Wilson 95% CI 91.7-99.7%) against an independent oracle, versus 66-80% for an LLM summary of the same capture, a mid-tier model reading the block matching a frontier one. The same compiler doubles as a demand-side cost instrument. Read off passive, pre-delegation human activity rather than agent rollouts, it supplies two parameters that agent-cost models assume but, to our knowledge, have not measured: the Routine Overhead Ratio R and the routine recurrence h. We report first values of R, a modeled upper bound, at 60-343x, and a delegable recurrence of 9.0% in-sample and 7.7% out-of-sample, for a realistic all-fleet token ceiling near 8%; a compiled routine replays deterministically with the model out of the loop, demonstrated live at zero model tokens on a guard-matched hit. Schema, compiler, and evaluation harness are open.