← 研踪 PaperTrailarXiv:2611.17874 · v1
What a Memory Preview Cannot Tell You: Ambiguity in AI Memory Permissions
首次提交 2026-11-13 16:04
版本更新 2026-11-13 16:04
雷达观测 2026-11-16 10:40
摘要
A memory rule states when an assistant may reuse a remembered event, and an editor can confirm a rule by previewing one use it allows and one it blocks. We ask what such a preview lets a person infer about the rule they saved. For an editor with six or twelve valid rules, we enumerate every rule compatible with a preview. Splitting the rules most evenly does not target the question a user cares about. For an explicit preference, two adaptive tests leave all three recommendation scopes open (for a one-off choice the outcome turns on a tie), while one test of transfer to another task settles the question. Weak previews are also the default. Under the intended rule, 36 of 39 possible allowed/blocked pairs contain a blocked example that no rule allows, and no pair identifies the rule. Three or four tests suffice here; when permissions depend on each other, a fixed checklist grows to six or nine and adaptive questioning needs at most five or seven. These counts use a specified rule vocabulary and fictional events. In a small pilot, 10 of 20 people who saw such a weak preview of a rule they had just chosen mispredicted, or were unsure about, at least one of two uses, and none of those 10 said the outcomes matched what they wanted. Whether better previews help people is untested.
作者备注:4 pages, 2 figures, 1 table. Code and data: https://github.com/tonni19/memory-preview-ambiguity
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-13 16:04 · 最新观测版本
What a Memory Preview Cannot Tell You: Ambiguity in AI Memory Permissions
A memory rule states when an assistant may reuse a remembered event, and an editor can confirm a rule by previewing one use it allows and one it blocks. We ask what such a preview lets a person infer about the rule they saved. For an editor with six or twelve valid rules, we enumerate every rule compatible with a preview. Splitting the rules most evenly does not target the question a user cares about. For an explicit preference, two adaptive tests leave all three recommendation scopes open (for a one-off choice the outcome turns on a tie), while one test of transfer to another task settles the question. Weak previews are also the default. Under the intended rule, 36 of 39 possible allowed/blocked pairs contain a blocked example that no rule allows, and no pair identifies the rule. Three or four tests suffice here; when permissions depend on each other, a fixed checklist grows to six or nine and adaptive questioning needs at most five or seven. These counts use a specified rule vocabulary and fictional events. In a small pilot, 10 of 20 people who saw such a weak preview of a rule they had just chosen mispredicted, or were unsure about, at least one of two uses, and none of those 10 said the outcomes matched what they wanted. Whether better previews help people is untested.
查看此版本解读 →查看此版本原文 ↗