@LinusEkenstam: I never liked .md Been using html for most context building since last year. My thesis has been, if it trained on the e…
Summary
Linus Ekenstam explains his preference for using HTML instead of Markdown when building context for AI, citing broader training data availability for HTML.
View Cached Full Text
Cached at: 05/10/26, 02:26 AM
I never liked .md
Been using html for most context building since last year.
My thesis has been, if it trained on the entire internet, surely there must be more html than .md?
And creating context that’s easier for me to digest was more important than using .md
Similar Articles
@trq212: https://x.com/trq212/status/2052809885763747935
The article argues that HTML is a superior output format for AI agents compared to Markdown due to richer information density, visual clarity, ease of sharing, and two-way interaction, and shares why the author and others at Claude Code prefer HTML.
@trq212: HTML is the new markdown. I've stopped writing markdown files for almost everything and switched to using Claude Code t…
The author explains why they have switched from writing markdown files to using Claude Code to generate HTML for them, arguing that HTML is the new markdown.
@namcios: Anthropic just killed Markdown. A Claude Code engineer published an article yesterday that could herald the start of a …
An Anthropic engineer argues that HTML should replace Markdown as the primary output format for AI agents, offering interactive interfaces and shared memory over static text reports.
Using Claude Code: The unreasonable effectiveness of HTML
A blog post by a Claude Code team member argues for using HTML instead of Markdown as the preferred output format for AI agents like Claude Code, citing benefits such as richer information density, visual clarity, ease of sharing, and interactive capabilities.
Using Claude Code: The Unreasonable Effectiveness of HTML
Simon Willison discusses the effectiveness of using HTML instead of Markdown as AI output format, highlighting benefits like SVG diagrams, interactive widgets, and rich explanations. Includes examples from Thariq Shihipar on Anthropic's Claude Code team and practical prompts for GPT-5.5.