斯坦福 Percy Liang 团队评估 AI 提出研究问题的能力
斯坦福 Percy Liang 找了 29 位数学、物理等领域的专家给 AI 出的研究题目打分,三分之一算有意思,结果挺值得看看。
斯坦福教授 Percy Liang 发布一项评估结果,测试 AI 能否提出有意思的研究问题,而不仅是解题。团队邀请数学、统计、计算机、物理四个领域的 29 位专家对 AI 生成的问题打分,结果显示其中约 1/3 被专家认为有研究价值。团队预期这一比例会随模型迭代继续上升,并认为这会影响学界与工业界中人机协作的分工方式。
Recent weeks have made it clear that AI excels at solving research problems. How good is it at proposing *interesting* research problems? Thanks to the ratings of 29 experts across math, stats, CS, physics, we found 1/3 were interesting, and we fully expect this to improve. This raises important questions about the desired relationship between {humans,AI} in {academia,industry}...