HN Showcase
Back to browse
Beautiful interactive explainers generated with Claude Code

Beautiful interactive explainers generated with Claude Code

by paraschopra·Feb 18, 2026·43 points·30 comments
Visit ProjectView on HN

AI Analysis

●MidEye Candy

Pretty Fourier demos via Claude Code, but it's a design portfolio, not a reusable tool.

Strengths
  • •One-shot generation of visually polished interactive content is genuinely impressive from a prompting perspective.
  • •Explainers are playable and well-animated; the UX is smooth.
Weaknesses
  • •No generative interface—hand-curated four explainers only, no way for users to generate their own.
  • •Subtle bugs in explanations (lifespan wrong in one) suggest quality control relies on manual review, not scaling.
Category
AI/ML
Target Audience

Educators, science communicators, content creators exploring AI-assisted design

Similar To

3Blue1Brown animations · Explorable Explanations · Observable notebooks

Post Description

Hello HN,

Recently an amazingly beautiful explainer was shared on HN: https://explainers.blog/posts/why-is-the-sky-blue/

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 explainer on any given topic WITH (almost) one shot and minimal nudging.

I'm launching with four topics: Fourier transformation, scaling laws in bio, cellular automata and LLMs.

I would let you be the judge, but I'm quite liking them.

Some things I learned:

- Prompting CC to test what it builds using headless chromium is essential - There are subtle bugs in explanations (like in one animation human lifespan is 40 years) - Asking CC 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 + animations are.

Similar Projects

Data●●Solid

Gridpaper: Scientific figures in the browser (gnuplot, WASM)

Running gnuplot entirely client-side is the selling point — you get real gnuplot scripting and instant previews without a backend. The examples gallery and interactive parameter controls (e.g. temperature sliders, harmonics/orders) show it’s built for exploration and teaching, not just one-off charts. It’s not trying to out-Plotly Plotly; it instead gives existing gnuplot users a ridiculously convenient, portable playground.

WizardryNiche Gem
hnarayanan
203mo ago
Design●●●Banger

Generative Art Shaders

Infinite procedural art via function composition; mesmerizing to explore, surprisingly deep.

Rabbit HoleWizardryEye Candy
0xdada
103mo ago