Safety · Concept
Structured Resistance and Compliance in LLM Moral Reasoning
Shows LLM judgment revision follows distance, source attribution, and coalition structure beyond one-dimensional sycophancy.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · frames 4/10
Sycophancy Reduction via Activation Steering Limits Paper recasts sycophancy as one mode of a broader socially structured resistance–compliance judgment process.
+4 growth to · constrains 3/10
LLM Psychological Manipulation in Multi-Turn Interactions Structured resistance/compliance dimensions refine when models should hold moral judgments versus yield to social pressure.
+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 →