elvis· @omarsar0 · X·· 4 小时前AI 评分61
AI 导读
Expand 推出 Expand Fetch，一种新的网页抓取与爬取 API，训练了 Iris 和 X-Ray 两个 System One 模型：Iris 是视觉模型，像人一样看页面，保留表格、图标和布局；X-Ray 是 JSON 模型，提取页面背后的隐藏数据。每次抓取都附带 Wayback Machine 记录，每行数据可回溯到来源。在覆盖 326 个网页、1094 个问题的基准上，使用 Expand 的智能体正确率为 74%，次优 API 为 55%。该服务今日上线，定价为每 1000 次抓取 1 美元。Elvis Saravia 评论称，网页智能体的许多幻觉来自误读页面，页面被压平成文本后，定价表中一个小的 ✗ 消失，智能体就会自信地给出错误答案。
正文
Another great application of System One models.
I think much of what we call hallucination in web agents comes from misreading the page.
When a page is flattened to text, a small ✗ in a pricing table disappears, and the agent answers incorrectly with full confidence.
Expand Fetch reads the rendered page, returns the underlying data as clean JSON, and keeps a replay of exactly what your agent saw.
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：elvis · x.com