@AnthropicAI collaborated with us on a review of the unredacted chemical and biological (CB) risk sections of their February 2026 Risk Report. After months of followup and hundreds of pages reviewed, we share our external review below.
SecureBio
@SecureBio
SecureBio is a research non-profit that works to advance biotechnology safely and prevent catastrophic pandemics
Joined January 2025
- We at SecureBio tested GPT-5.6 Sol’s biorisk-related capabilities: virology and pathogen knowledge, niche scientific knowledge, agentic bio capabilities, and bio AI tool usage. GPT-5.6 Sol beat every prior model on three of our four bio knowledge benchmarks and scored above our
- We are pleased to announce our first evaluation of biosecurity-relevant safeguard effectiveness, BioTIER (Biological Targeted Information for Exclusion and Refusal). This evaluation fills a critical gap in the evaluations ecosystem by measuring both safety and utility of AI
- What can we do to prepare for a "Bio Mythos" moment? @BreenColeman and @hodanomaar expand on the relationship between cyber and biological capabilities of advanced AI models and provide three recommendations for policymakers: (i) Continue giving access to advanced models to
- We do a lot of wastewater sequencing, 80 billion reads a week to be exact. In sewersheds across the country we monitor for pathogens that can cause pandemics using ultradeep, metagenomic sequencing.
