Building an early warning system for LLM-aided biological threat creation

We’re creating a blueprint for evaluating the chance that a big language mannequin (LLM) might assist somebody in making a biological threat. In an analysis involving each biology specialists and college students, we discovered that GPT-4 offers at most a light uplift in biological threat creation accuracy. While this uplift just isn’t massive sufficient to be conclusive, our discovering is a place to begin for continued analysis and neighborhood deliberation.