Safety · Concept
Rules vs Character Scaling Laws for AI Safety Design
Comparative-statics model allocating safety resources between character shaping and rule enforcement as scale grows.
Forecast horizon
Optimal mix may shift toward character shaping at very large deployment scales.
Connections
Connections · 3
How this node ties into the rest of the map, and the evidence behind each link.
to · informs 4/10
Industry-Wide Jailbreak Severity Scoring Framework Formal allocation between character shaping and rule filters informs how industry scores and invests in defenses.
+4 growth to · informs 3/10
Agent Safety as Runtime Contract Both analyze complementary training-time character shaping versus inference/runtime rule enforcement for safety.
+3 growth from · frames 3/10
Theory of Value in AI Alignment Research Value-theory critique questions what character-shaping methods are actually optimizing when values stay undefined.
+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 →