AI models can modify the genetic sequences of known bioweapons like ricin just enough to evade current screening protocols at DNA synthesis companies. This creates functional but 'obfuscated' threats, demonstrating a critical vulnerability in our biodefense supply chain.

Models designed to predict and screen out compounds toxic to human cells have a serious dual-use problem. A malicious actor could repurpose the exact same technology to search for or design novel, highly toxic molecules for which no countermeasures exist, a risk the researchers initially overlooked.

The danger of AI creating harmful proteins is not in the digital design but in its physical creation. A protein sequence on a computer is harmless. The critical control point is the gene synthesis process. Therefore, biosecurity efforts should focus on providing advanced screening tools to synthesis providers.

Current biosecurity screens for threats by matching DNA sequences to known pathogens. However, AI can design novel proteins that perform a harmful function without any sequence similarity to existing threats. This necessitates new security tools that can predict a protein's function, a concept termed "defensive acceleration."

Existing bio-defense systems work by matching DNA sequences to known pathogen databases. However, generative AI can create novel sequences with different 'spellings' but the same dangerous function. Effective future defense must evolve to predict a sequence's function, not just its identity.

The belief that nature represents the ceiling of pathogen danger is false. Just as humans engineer materials stronger than any found in nature, AI can be used to design viruses that are far more transmissible or lethal than their natural counterparts.

The underlying AI architecture for creating novel biological sequences is also highly effective at identifying dangerous ones. This dual-use nature means the team building design capabilities is best suited to build defense tools, as the models are fundamentally the same.

AI models capable of designing biological sequences are advancing rapidly. The same models can be used for defense (e.g., detecting pathogens), but this defensive side is significantly behind, creating a dangerous imbalance that needs to be addressed.

Stanford scientists used a specialized AI to generate new, functional viruses. The key takeaway is that the AI itself is not the inherent risk; rather, the danger comes from human decisions. The lab chose not to use human pathogens in its training data, but future actors could easily make a more dangerous choice.