Claude's WebFetch never reads raw HTML: pages are extracted to markdown and answered by a small model
gaganghotra_ · x · 2026-09-23
Natzir Turrado corrects two misreadings of the new Claude tools: fetch tools never read raw HTML — they extract to text/markdown first ("markdown" plus legacy "traf" in Opus 4.7) — and fan-out with parallel subagents was already described by Anthropic in June 2025; the only novelty is a small fast model reading the markdown. His experiment on 15 HTML layout variants maps which page structures survive LLM extraction (no JS execution, Readability-style extraction), with SEO implications: money-page rankings aren't enough, evidence must hold up per decision criterion.
More from Models
- GPT-6 Sol accused of ignoring configured skills that work fine on GPT-5.6 — Aber-so-richtig · 2026-09-23
- Opus 5.5 ultra wows with 4-agent, 90-minute fully-from-scratch build — repligate · 2026-09-23
- No Kimi release this week, says leaker: Moonshot staff go on holiday Friday — ChrisGPT · 2026-09-23
- Screenshot suggests GPT-5.6 Sol is free for ChatGPT Go subscribers on Windows — sam619007 · 2026-09-23
- Opus 5.5 wins the day as GPT-6 Sol skips ChatGPT, sparking model debate — koltregaskes · 2026-09-23
- Opus 5.5 becomes a daily driver: faster, cheaper than Opus 5, plus reset credits — addyosmani · 2026-09-23