AI HOT (Curated Pool)May 9, 2026, 05:00 UTC+8

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: HKR-H/K/R all pass, but this is a workflow tip rather than a Claude release. As a quality Claude Code tutorial, it sits in the 72–77 band, with Simon Willison’s source authority clearing featured.

Read the original ↗Export Markdown

Take

HTML output in Claude Code is a review artifact, not presentation sugar. Simon’s example has a concrete hook: GPT-5.5 generated an interactive Linux exploit explainer with SVG diagrams, widgets, in-page navigation, and styled sections; Thariq’s prompt even asks for PR diffs with inline margin annotations and severity colors. The old Markdown default came from the GPT-4 8,192-token era, where saving tokens beat richer structure. That tradeoff has moved.

I buy the workflow, with one caveat. For code review, incident writeups, and unfamiliar subsystems, HTML gives the model a real UI surface. For exploit analysis, the same affordance makes a local privilege-escalation PoC easier to operationalize. “Defensive explanation” and “usable tutorial” are separated by prompt wording, not a hard product boundary.

Source: AI HOT (Curated Pool) · simonwillison.net
Published: May 9, 2026, 05:00 UTC+8 · May 9, 2026