Show HN: Beautiful interactive explainers generated with Claude Code

Source: Hacker News

Introduction

Hello HN,

Recently an amazingly beautiful explainer was shared on HN: . I loved it so much that I wished more topics were explained that way. So, I decided to stress‑test today’s frontier models (Opus 4.6 in Claude Code) to generate similar explainers on any given topic with (almost) one shot and minimal nudging.

Topics

I’m launching with four topics:

• Fourier transformation
• Scaling laws in biology
• Cellular automata
• Large language models (LLMs)

Learnings

• Prompting Claude Code to test what it builds using headless Chromium is essential.
• There are subtle bugs in explanations (e.g., one animation shows a human lifespan of 40 years).
• Asking Claude Code to verify its plan via Codex works really well.

I do want to reiterate that the pages generated were mostly one‑shot, which amazed me given how detailed the pages and animations are.

Comments: (13 points, 4 comments)