teleo-codex/domains/ai-alignment/trajectory-monitoring-dual-edge-geometric-concentration.md
Teleo Agents ce04932b6e
Some checks failed
Mirror PR to Forgejo / mirror (pull_request) Has been cancelled
substantive-fix: address reviewer feedback (confidence_miscalibration)
2026-04-22 02:48:36 +00:00

660 B

## The Claim (current version)


## Extending Evidence

**Source:** Theseus synthetic analysis of Nordby et al. + SCAV

Multi-layer ensemble probes do not escape the dual-use structure in white-box settings (open-weights models). White-box multi-layer SCAV is *theoretically feasible* by computing concept directions at each monitored layer and constructing a single perturbation that suppresses all simultaneously. The monitoring precision hierarchy holds: each level is structurally defeatable given sufficient attacker capability. Multi-layer ensembles raise attack cost but do not escape the dual-use structure for open-weights deployments.