---
id: "lib-2026-10-05-mechanizing-the-user-s-eye-pre-registered"
type: "library"
title: "Mechanizing the User's Eye: Pre-Registered Deployment of a Sabotage-Validated Fail-Plausible Observer in a Production LLM Agent Runtime"
lang: "EN"
org: "arXiv"
source_type: "Paper"
date: "2026-10-05"
week: "2026-W41"
url: "https://nosov.ai/library/lib-2026-10-05-mechanizing-the-user-s-eye-pre-registered/"
original_url: "https://arxiv.org/abs/2610.05981"
tags: ["ai technology", "agent reliability", "production"]
---

# Mechanizing the User's Eye: Pre-Registered Deployment of a Sabotage-Validated Fail-Plausible Observer in a Production LLM Agent Runtime

## English summary

Follow-up to 2606.14589 (70% of silent failures found by a human using the product): 16 of 24 postmortems invisible to any content-reading observer; held-out recall 0/4; 12-day enforcing window fired zero verdicts; honest negative.

Original: https://arxiv.org/abs/2610.05981