{"data":{"id":"ead5dd30-9b39-489d-b5aa-c16b7178a147","title":"Using Claude Code: The Unreasonable Effectiveness of HTML","summary":"This article discusses using HTML instead of Markdown when requesting output from Claude, an AI assistant. HTML allows Claude to create richer explanations by including SVG diagrams, interactive widgets, and better navigation, which was less practical with older language models that had strict token limits (tokens being units of text that count toward a model's processing capacity).","solution":"N/A -- no mitigation discussed in source.","labels":["research"],"sourceUrl":"https://simonwillison.net/2026/May/8/unreasonable-effectiveness-of-html/#atom-everything","publishedAt":"2026-05-08T21:00:11.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":["Anthropic"],"affectedVendorsRaw":["Anthropic","Claude","Claude Code","GPT-4","GPT-5.5"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-05-08T21:00:11.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.75,"researchCategory":null,"atlasIds":null}}