Defining dangerous DNA with the Sequence Biosecurity Risk Consortium (SBRC)

Defining which sequences are dangerous enough to screen for, so providers and regulators screen consistently

Continued development of Commec, IBBIS’s open-source DNA screening tool

Next year of Commec (the Common Mechanism), the free, open-source, globally-available DNA synthesis screening tool hosted by IBBIS

safely.bio: Customer screening for DNA synthesis providers

Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats

Scaling adoption of synthesis screening outside the US and EU

An outreach campaign from IBBIS to rapidly increase adoption of effective synthesis screening tools during a critical regulatory window.

Safeguarding DNA Synthesis from Biological Risks Posed by Advanced AI

We will test whether circuits in protein language models can detect function-preserving redesigns of known toxins that evade homology-based DNA-synthesis screen

BioRAG-Guard: Poisoning Evals for Biological AI Agents

An open-source benchmark and defense toolkit for testing whether corrupted biological databases can hijack retrieval-augmented AI agents used in genomics, prote

Animal Welfare in Ukraine: #SaveVets_SafePets

Scaling veterinary interventions to mitigate zoonotic risks and animal suffering at the intersection of conflict and public health in Ukraine’s frontline zones.

Isolating CBRN Knowledge in LLMs for Safety - Phase 2 (Research)

Expanding proven isolation techniques to high-risk capability domains in Mixture of Expert models

Operating Capital for AI Safety Evaluation Infrastructure

Enabling rapid deployment of specialized engineering teams for critical AI safety evaluation projects worldwide

Eradicate the hidden factory farming of feeder rodents

Developing and commercializing an alternative to feeder rodents—tackling one of the most neglected and high-suffering forms of factory farming.

Clean Indoor Air for Schools

Accelerating the adoption of air filters in every classroom

Building Effective Giving ecosystem in India

Funding circles and advisory to fund high impact non-profits

Can Fragile Labs Use AI Safely?

AI-Biosecurity Stress Test for Public Health Laboratory System in Liberia, West Africa

Fund Sentinel for Q1-2025

A foresight and emergency response team seeking to react fast to calamities

Philanthropic advising

80,000 Hours

We provide research and support to help people move into careers that effectively tackle the world’s most pressing problems.

Research Staff for AI Safety Research Projects

Preventing Worst Case Pandemics Symposium @ Cambridge

A Cambridge Biosecurity Hub and Cambridge Infectious Diseases Symposium on Avoiding Worst-Case Scenarios

Grant to establish an AI safety lab and fellowship from India

Focusing more on the intersection of red teaming and interp, while creating a strong rooted community.

Real-Time Airborne Biothreats - Preventing the Next Biological Disaster