Safety · Concept
ASR Error Safety Risks in Voice-Controlled Embodied AI
Simulated speech-recognition errors increase harmful ambiguity and weaken refusals in embodied AI safety benchmarks.
Forecast horizon
Voice interfaces need ASR-robust safety evals beyond text-only agent benchmarks.
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · informs 3/10
Risks of Mass AI Agent Interactions ASR-induced unsafe plan execution shows perception-stack faults as an embodied agent safety pathway.
+3 growth from · supports 3/10
GuardianBench: Same-Scene Instruction-Contrastive Embodied Safety Benchmark Both isolate latent embodied hazards where instruction or perception context flips a safe scene into harm.
+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 →