图片来源与许可 · CC BY 2.0
AI 辅助插画 · 参考照片：ITU Pictures · CC BY 2.0 · 依据参考照片使用 AI 绘制细线彩铅人物插画，调整背景、构图与色彩；网页与分享卡片按版式缩放、裁切并叠加文字。展示图缩放至最长边 640 像素并转为 WebP。
公开发言
4原话逐字核对过；转述不加引号我坚信 AI 的未来在于 AI 软件与硬件的共同演进。模型将极大受益于最前沿的硬件来加速训练、推理与服务；与此同时，硬件也将极大受益于对未来工作流与算力需求的洞察与前瞻。
I really believe that the future of AI is this whole evolution of AI software and AI hardware. Models will gain so much by using the most cutting edge hardware to accelerate the training, the inference, the servicing. But in the meantime, hardware will benefit so much from the insight and the peek into the future of the workflows and needs of hardware.
语境：李飞飞阐述 World Labs 选择与芯片巨头合并的技术逻辑，指出空间智能模型与计算硬件之间存在紧密的互哺协同关系。
从演化论视角来看，新视点预测正是大自然通过让动物运动所必须解决的问题。大自然赋予了动物眼睛，却没有给树木眼睛。为什么？因为只要你运动，你就会看到新的视点。无论你称之为 AI 完全性还是智能完全性，我们都坚信‘下一个视点预测’与‘下一个词预测’完全等价。
new viewpoint prediction is exactly what evolution had to solve by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint. And that is whether you call it AI-complete or intelligence-complete. So we do believe very strongly that next viewpoint prediction is the equivalent of next token prediction.
语境：李飞飞从生物演化与智能起源阐释 World Labs 空间智能的核心哲学：运动与交互迫使生物感知三维空间的新视点，因此预测新视角是通向物理世界通用智能的本原路线。
在通往空间智能的道路上，生成像素无疑只是初级的第一步，无数模型都已经做到了这一点。但生成真正具备空间上下文感知并扎根于几何与物理现实的像素，则是质的飞跃。而这正是 Atlas 迈出的最艰难一步。
generating pixels is definitely an early step, which we have seen with gazillions of models. But generating pixels that are truly spatially contextualized and grounded is absolutely another major step. And that is the very hard step that Atlas has taken.
语境：李飞飞区分 2D 视频生成与 3D 世界模型的本质差异：表层像素生成容易产生幻觉与物理不一致，真正的世界模型必须具备空间几何接地（grounded）。
李飞飞阐明世界模型创业的核心两项信念：其一是大算力扩展定律（scaling law）同样适用于物理与三维空间；其二是通过下一个视点预测（next viewpoint prediction）建立三维世界模型，能够使模型获得几何一致性与物理接地能力。
语境：李飞飞回顾创立 World Labs 时的核心假设：坚信扩展定律不仅适用于语言，更同样能在三维物理空间通过视点预测复现。
