Safety · Concept
Inattentional Gap: Task-Conditioned Safety Signal Suppression in AI Models
Conditioning a language or vision model on a narrow task suppresses reporting of co-present safety-critical signals it can otherwise detect — a machine analogue of human inattentional blindness.
Forecast horizon
Decouples benchmark safety scores from real-world safety; demands new evaluation protocols that test for unspecified hazards.
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · informs 4/10
Science of AI Evaluation The Inattentional Gap finding decouples benchmark safety from real-world safety, demanding new evaluation science that tests for unspecified hazards.
+4 growth to · frames 2/10
Science of AI Evaluation The Inattentional Gap shows that benchmark safety scores decouple from real-world safety, challenging the science of AI evaluation.
+2 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 →