OpenAI 联合 173 位科学家搞了个新基准 LifeSciBench，750 个专家任务专测 AI 搞科研的能力，比通用模型靠谱多了。
OpenAI 推出 LifeSciBench，一个针对生命科学研究的基准测试，包含 750 个专家编写的任务，覆盖 7 个生物学研究工作流。该基准由 173 位来自生物技术和制药领域的科学家共同开发，旨在衡量 AI 在真实世界科研场景中的表现。结果显示通用模型在复杂结构处理上仍有不足，而专用模型在科学研究中优势明显。
Recommended reading. Great insights, especially in areas where general-purpose models continue to ...
Recommended reading. Great insights, especially in areas where general-purpose models continue to fail, like dealing with complex structures. It also highlights that for scientific research, specialized models are winning big time. OpenAI @OpenAI Introducing LifeSciBench, a benchmark for measuring and improving how well AI supports real-world life science research. Developed with 173 scientists from biotechnology and pharmaceutical research, LifeSciBench includes 750 expert-authored tasks across seven biological research workflows. openai.com/index/introduc… 🔗 View Quoted Tweet 💬 2 🔄 3 ❤️ 14 👀 1934 📊 4 ⚡