2026-05-12 HTML as the New AI Output Format

Canonical version: 2026-05-12 HTML as the New AI Output Format.

HTML is opening up a richer way to explore AI-generated ideas. Not as a replacement for markdown — markdown remains excellent for text-first content — but as another canvas, one where ideas can include animations, interactivity, charts, layout, and structure that text alone can't carry.

Two voices made the case this week: Thariq Shihipar (Claude Code team) published a thorough exploration of HTML as an AI output format, and Andrej Karpathy framed it as part of a broader spectrum of how humans and AIs exchange information.

The Core Idea

Markdown is great for notes, drafts, and transient conversation. But some ideas want more: a working visualization of an algorithm, a slider to tune a design parameter, tabs in a long spec, hover-revealed detail in a report, an SVG diagram of a system. HTML gives the AI a canvas for those moments.

What HTML adds beyond markdown:

• Tables with proper structure and CSS styling
• SVG diagrams, illustrations, flowcharts
• Animations and transitions
• Interactive widgets (sliders, toggles, buttons) via JavaScript
• Spatial layouts (absolute positioning, canvases)
• Mobile-responsive structure for longer documents

The result: AI responses become more interesting and more fun to actually explore.

Karpathy's Framing

Karpathy frames AI output as a spectrum, not a ladder where each rung replaces the previous one:

1. Raw text → 2. Markdown → 3. HTML → 4. Interactive neural videos/simulations

Each format has its moment. The key insight: audio is the preferred human input to AI; richer visual formats are increasingly the preferred AI output to humans. Roughly one-third of the human brain is dedicated to visual processing — when ideas benefit from being seen rather than just read, moving up the spectrum pays off.

Practical Impact

• Ask your AI: "Structure your response as HTML" — that's all it takes
• Good fits: specs, code reviews with annotated diffs, design prototypes, research reports, custom editing UIs, interactive explainers
• Always include an export button ("copy as JSON / copy as prompt") to bring interactive changes back into the AI conversation
• Tradeoff: HTML takes 2–4× longer to generate than markdown, and HTML diffs are noisier in version control — so reach for it when the visual/interactive payoff justifies the cost

Connection to Notes and Wikis

This pairs naturally with LLM Wiki and vault notes: feed a set of permanent notes or wiki articles into a prompt and ask for an HTML page or site. The combination of rich vault context and HTML output enables shareable, interactive knowledge artifacts — no publishing infrastructure required, no replacement of the underlying markdown notes.

See also: Structuring AI responses as HTML

References

• trq212 — HTML as AI output format
• Andrej Karpathy — vision as preferred AI output

Related

• Structuring AI responses as HTML
• LLM Wiki

About Sébastien

I'm Sébastien Dubois, and I'm on a mission to help knowledge workers escape information overload. After 20+ years in IT and seeing too many brilliant minds drowning in digital chaos, I've decided to help people build systems that actually work. Through the Knowii Community, my courses, products & services and my Website/Newsletter, I share practical and battle-tested systems.

I write about Knowledge Work, Personal Knowledge Management, Note-taking, Lifelong Learning, Personal Organization, Productivity, and more. I also craft lovely digital products and tools.

If you want to follow my work, then become a member and join our community.

Ready to get to the next level?

If you're tired of information overwhelm and ready to build a reliable knowledge system:

• 📚 KM for Beginners — 10+ hours of structured video lessons
• 🚀 Obsidian Starter Kit — Ready-made vault with 40+ templates
• 💼 Knowledge Worker Kit — Complete guides + lifetime community
• 🦉 1-on-1 Coaching — Personalized guidance
• 🎯 Join Knowii — Community + ALL courses & tools