OpenAI Blog company blog
Building an early warning system for LLM-aided biological threat creation
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…
- Points
- 118
- HN comments
- 176
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningScience & Space2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jan 31, 2024 | Building an early warning system for LLM-aided biological threat creation by minimaxir | 118 | 176 |
