CGI 如何一夜杀死定格动画
推荐指数 41.0 NO. 020 · 2026.07.13
发布2026/07/12Score111Comments47
为什么值得看
1993年《侏罗纪公园》制作期间，斯皮尔伯格本打算用传统定格动画拍摄恐龙，ILM团队用CGI做出了一只照片级真实的霸王龙测试片段，直接改变了电影工业的技术路线。这是技术颠覆式创新的经典案例：成熟技术被新范式瞬间取代，决策者甚至没来得及犹豫。
编辑判断
这个案例常被引用却少被深究的是'组织惯性'问题。Tippett 工作室当时已经投入数月做恐龙定格动画，斯皮尔伯格本人也公开质疑 CGI 能力，但一个 45 秒的测试片就让千万级预算转向全新技术栈。对 AI 创业团队的启示是：toB 产品的替换成本不是说服决策者，而是做出一个让决策者无法向老板解释'为什么不换'的 demo。
另外常被忽略的是 ILM 的'秘密武器'——他们此前在《终结者2》液态金属人和《深渊》假水柱上积累了大量光线追踪和流体模拟经验，T-Rex 测试并非从零突破，而是技术复利的一次兑现。这解释了为什么真正的技术颠覆往往来自边缘业务的积累，而非主攻方向的线性延伸。
社区反馈
意见分歧 46 条评论
核心争论：LLM 提升产出量是否等于真正进步，还是加剧质量危机与不合理预期
相关内容
I mostly like this article but > Those who refuse to use an LLM will fall behind because they won't be able to produce as much Seems like a silly and needlessly aggressive take. Fall behind what? Able to produce "as much" what? I've never been evaluated on volume in my life. Nor have co workers who
Yes, I dislike this kind of take so much. It keeps being repeated as a truthism and a way of putting down people that don't do what the speaker wants. It's fine to disagree, but there's no need to get such a threatening tone. A lot of tech jobs seem to be only about sheer output volume, with quality
My experience with regard to quality is quite the opposite. With LLM at my disposal, I had the time- and effort-budget to expand test suites considerably, I was even able to attack a somewhat thorny question of reproducible builds on MSVC, which is not exactly friendly towards determinism. These tas