Chubby♨️· @kimmonismus · X·· 4 小时前AI 评分59
AI 导读
Expand Fetch 发布新的网页抓取与爬取 API，包含视觉模型 Iris 和 JSON 模型 X-Ray，保留表格、图标与页面布局，并附带 Wayback Machine 让每行内容可回溯来源。官方称在 326 个网页、1094 道题的基准上，使用 Expand 的智能体答对 74%，次优 API 为 55%；定价为每 1000 次抓取 1 美元，已在 expand.ai 上线。作者补充说，把页面压成纯文本会丢掉定价表里的 ✗ 等细节，导致智能体答错。
正文
Agents are only as good as the page they think they saw.
A tiny ✗ in a pricing table means “not included.” Flatten the page to text and it vanishes, and the agent confidently gets it wrong.
@TimSuchanek’s Expand Fetch keeps tables and icons intact and saves the page, so you can see exactly what the agent read. Pretty pretty useful! :)
Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets basic questions wrong. Traditional Markdown APIs lose critical details. So we trained two System one models to change that: Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts. X-Ray, a JSON model that uncovers the hidden data behind every page. Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw. Three products. One API. On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%. Available today at $1 per 1,000 fetches. Try it at http://expand.ai在 X 查看被引用的帖子
来源：Chubby♨️ · x.com