Building an early warning system for LLM-aided biological threat creation
What changed
We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in biological threat creation accuracy. While this uplift is not large enough to be conclusive, our finding is a starting point for continued research and community deliberation.
Why it matters
A concrete addition to Practical AI: Tools, Models & Frameworks: it changes what's available to builders today rather than being general commentary.
How it compares
Related prior coverage to compare against:
- Measuring AI’s capability to accelerate biological research
- Fine-tuning GPT-3 to scale video creation
- Introducing new capabilities to GPT-Rosalind
Sources
- Building an early warning system for LLM-aided biological threat creation (openai-blog)primary