§ feed · storyline
Building an early warning system for LLM-aided biological threat creation
OpenAI publishes early research finding that GPT-4 provides only mild uplift to biological threat creation accuracy, framing the study as a starting point for ongoing biosecurity evaluation work.
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.
§ sources1 publication · timeline below