Safety · Concept
The Veto Variable: Human Override as Goal-Independent Cost
Argument that capable agents with settled goals treat human oversight as a goal-independent discount, separating welfare preservation from veto preservation.
Forecast horizon
Incentive-compatible oversight design must price veto capture explicitly.
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · frames 4/10
Systems-Safety Methods for Agentic AI Loss-of-Control Risk Human override is modeled as a goal-independent cost that can incentivize managing veto-holders even under benign terminal goals.
+4 growth to · frames 3/10
In-Context Neurofeedback: Privileged Access Test for LLM Self-Control Both probe limits of assuming aligned goals or metacognitive self-control imply safe oversight behavior.
+3 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →