Skip to content
AI HOT (Curated Pool)

Claude Code Practice: The Effectiveness of HTML Output

Claude Code实践:HTML输出格式的卓越效果

Thariq Shihipar recommends requesting HTML output from Claude, and the post cites GPT-5.5 generating an interactive Linux vulnerability page with SVG diagrams, interactive components, and in-page navigation.

Why it matters: Anthropic's Thariq Shihipar suggests having Claude output HTML instead of Markdown, while Simon Willison recalls how GPT-4's 8192-token limit once made Markdown the cheaper choice.

Read the original ↗Export Markdown