Safety · Concept
ABC-Bench: Agentic Bio-Capabilities Benchmark
Benchmark for evaluating agentic AI biological capabilities relevant to biosecurity risk assessment.
Forecast horizon
All tested agents outperformed median expert humans, raising urgent biosecurity governance questions.
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
from · tracked by 4/10
Dual-Use AI Capabilities and Bioterrorism Risk ABC-Bench was designed to measure agentic biosecurity-relevant capabilities relevant to dual-use AI risks.
+4 growth to · tracked by 4/10
Dual-Use AI Capabilities and Bioterrorism Risk SciConBench evaluates AI agents' scientific synthesis capabilities in health domains, relevant to dual-use biosecurity risk assessment.
+4 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 →