决策模型Jev挑战电车难题
推荐指数 59.0 NO. 016 · 2026.10.16
发布2026/10/15Score154Comments77
为什么值得看
Jev等新一代"决策模型"以远低于LLM的成本输出带概率的选择而非文本，作者测试了它们处理经典伦理困境的能力。这揭示了AI从语言理解向实际决策跃迁时，概率化输出与道德判断之间的张力。
编辑判断
决策模型的真正战场不在哲学思辨，而在高频低延迟的自动化决策场景——比如实时竞价、风控拦截、推荐系统重排序。这些场景目前靠规则引擎或轻量模型硬撑，LLM又太贵太慢。
Jev的输出格式（概率分布+离散选择）天然适合接入现有的AB测试和bandit框架，但关键问题是校准性：模型说80%置信度，实际是否真的是80%？这在医疗、金融等高风险领域是生死线。
如果你在做需要毫秒级响应的决策系统，建议先跑一组校准曲线测试，别被"比LLM便宜100倍"的叙事带偏了核心指标。
社区反馈
意见分歧 71 条评论
核心争论：决策模型的概率输出是否可信，以及能否承担真实道德决策
Hey, I'm Zach, the author of this. I had this idea as soon as Jev appeared: how would Jev and other decision models handle the Trolley Problem? So I ran Jev and 13 other models through many different versions of the question. I used resampling and multiple variations and orderings of each question s
It's well done, the thoughtfulness shows. This is going into the speedlink folder for resharing, going to be using it right now!
Thank you! I did not go into this with any sense of what the results would be--I was kind of shocked. I reran it from scratch this week the results held up across the board.