
Ladder from text to video explained with the Pythagorean theorem
32 views · 0 likes · 0 saves · 0 reposts · Posted Oct 3, 2026 · 3:42 · Explainers
OUR NOTEA 3.7-minute Chinese explainer interpreting a Karpathy post on how AI answers can move from text to diagrams, interactive pages and video, using the Pythagorean theorem as the running example with subtitles and step tabs.
用 Opus 5.5 做了个视频来更加直观感的受一下 Karpathy 这个推文里想要表达的内容THE PROMPT
The creator didn't publish a prompt for this one. The post text is below.
MAKE ONE LIKE THIS
Three steps, using what the creators in this index used.- 1 · Copy the prompt
This creator didn't share a prompt. Start from our template instead.
PROMPT TEMPLATE → - 2 · Long piece? Give Claude a framework
- RavenMulti-agent research, coding and design orchestration★ 4.1k
- vox-directorPaper-collage style explainer and ad videos★ 2.1k
- manim_skill3Blue1Brown-style math and educational animation★ 1.1k
- 3 · Render it to MP4
For a longer piece like this one, render with a framework so the timing is exact on every take.
CLAUDE CODE + HYPERFRAMES / REMOTION →
The creator didn't name their tools. Most videos like this are HTML, canvas or SVG animation written by Claude and screen-recorded or rendered to MP4 — how that works.
Anthropic 确实发生了一些微妙的变化,员工逐渐在 X上公开发声了,也越来越倾听用户的声音了。Karpathy 自从加入 Anthropic 后,很少有时间发 X,这次随着 Opus 5.5 做动画的能力深受大家的,他也发表了一些观点。 过去我们把 LLM 当成一个“更聪明的聊天框”,所以默认输入是文字,输出也应该是文字。 但随着模型的代码能力越来越强,这个假设正在失效。 如果最终目的是“让人理解一件事”,那最好的输出未必是一篇 3000 字的文章,而可能是一张图、一个可交互网页、一个动画,甚至是一段专门为你生成的讲解视频。 我觉得这里更重要的变化是: 软件正在从「产品」变成一种「一次性的信息表达形式」。 过去做一个网页、动画...
Indexed Oct 7, 2026, 11:34 AM · Views as of indexing. Video and post © their creator.