---
title: "CBRN"
description: "2 posts about CBRN, summarised, each linking to the original."
---

# CBRN
> 2 posts about CBRN, summarised, each linking to the original.

## Articles

### [Activating AI Safety Level 3 protections](https://yomu.fyi/post/activating-ai-safety-level-3-protections.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Author: Anthropic
- Published: Nov 13, 2026
- Type: Announcement

Anthropic has activated AI Safety Level 3 (ASL-3) protections for its Claude Opus 4 model, a higher standard than the ASL-2 baseline used for all previous models. The decision was proactive, made before determining whether the model’s capabilities actually require the enhanced measures. ASL-3 deployment measures focus narrowly on preventing the model from assisting with extended, end-to-end CBRN weapons workflows. The approach includes Constitutional Classifiers that monitor inputs and outputs, a bug bounty program, and threat intelligence partnerships. Security controls include over 100 measures such as two-party authorization for model weight access and egress bandwidth controls that limit outbound data flow to prevent weight exfiltration.


### [A new initiative for developing third-party model evaluations](https://yomu.fyi/post/a-new-initiative-for-developing-third-party-model-evaluations.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Author: Anthropic
- Published: Oct 14, 2026
- Type: Announcement

Anthropic announced a new initiative to fund third-party organizations to develop evaluations for measuring advanced AI capabilities and safety risks. The initiative prioritizes three areas: AI Safety Level assessments for cybersecurity, CBRN, model autonomy, and other national security risks; advanced capability and safety metrics including science, harmfulness, multilingual, and societal impacts; and infrastructure, tools, and methods for evaluation development. The company seeks evaluations that are sufficiently difficult, not in training data, efficient, high-volume, and developed with domain expertise. Anthropic offers funding and direct collaboration with its domain experts from Frontier Red Team and other teams. The goal is to catalyze a robust third-party evaluation ecosystem to address the current limited landscape where demand for high-quality safety evaluations outpaces supply.
