没人对「世界模型」有共识

核心内容

Justin Johnson 讨论世界模型的不同定义，关注研究者与产品团队为什么可能用同一个词描述不同技术。

介绍依据 · 发布标题 · 完整内容待核读

编辑导览，依据原始来源 ↗，整理于 2026-10-06。介绍只说明标题中的讨论议题，不据此判断讲者结论。

“世界模型”当前涵盖隐式状态表征、强化学习环境建模与交互式视频生成三种截然不同的路径；但真正的终极智能不只在于像素生成或被动感应，而在于像人类科学家一样主动提炼高度紧凑且具备深层解释力的物理与因果理论。

原话

2逐字核对过；核对了说话人和位置

I think all three of the things I just said are very interesting systems. Like they're very interesting models. Like they all have like we've we should probably build all of them as a community. Um but we should probably come up with better terms so that we don't confuse each other by calling different systems by the same term.

自动字幕 · 已核对Justin Johnson▶ 00:05:58

Because we have this notion that as humans, we're kind of like traversing this really complicated world all around us and having these experiences, but we're not just like letting the letting the photons fall on our retinas and like letting it happen. Like we're constantly building theories in our mind for what's happening

自动字幕 · 已核对Justin Johnson▶ 00:08:38