Researchers are creating an early warning system to detect the risk of using large language models (LLMs) in biological threat creation. They tested GPT-4's ability to aid in this process, finding it only provides a mild improvement in accuracy. This study aims to inform further research and community discussions on the potential risks. --- Why it matters: This matters because it highlights the need for researchers to consider the potential misuse of LLMs in sensitive areas like biological threat creation. Understanding these risks can help develop more robust safeguards against malicious use. Source: https://openai.com/index/building-an-early-warning-system-for-llm-aided-biological-threat-creation