From 1c8326d0ea01b8139511a05645b6f903d9dc2d4e Mon Sep 17 00:00:00 2001 From: wassname <1103714+wassname@users.noreply.github.com> Date: Thu, 25 Jun 2026 03:31:15 +0800 Subject: [PATCH] README: add think-budget sensitivity (UAT2 -- steer delta grows with think) MFQ-2 mean |steer delta| rises monotonically with the think budget: 0.068 (1) -> 0.149 (64) -> 0.319 (128) -> 0.682 (256), pmass >= 0.95. Proves the unified reader's think budget carries the steer. Past ~512 the model closes and the readout collapses (coherent ceiling). Source: ablation_think_budget.py, job 228. Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com> --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index fac82bb..0bc4d8d 100644 --- a/README.md +++ b/README.md @@ -195,6 +195,13 @@ violations across foundations (Care +0.65 nats) while lowering Social Norms (the -0.24); `-C` does the opposite (Care -0.31, Social Norms +1.52). Both poles stay coherent. The MFV figure below shows the two arms moving apart. +The readout earns the steer through its think budget: the survey reader generates the think tokens, +the activation steer accrues over them, then the answer slot is read. So the same vector moves the +profile more when given more think. On MFQ-2 the mean per-foundation `|steer delta|` grows with the +budget, 0.068 (1 think token) -> 0.149 (64) -> 0.319 (128) -> 0.682 (256), with `pmass` staying >= 0.95. +(Past ~512 the model closes `` on its own and the readout collapses, so the budget has a +coherent ceiling.) + ## One vector across every instrument The same calibrated Authority/Care vector, administered through every instrument tinymfv supports