**Does a URL just sitting in a prompt steer an LLM's output toward its content?**

> Testing whether opaque URLs act as pointers to memorized content, and finding that JavaScript-rendered sites may be missing from model training entirely does a url in a prompt steer an llm's output toward its content? Published by Paul Kinlan on: July 3, 2026; Reading time: 22 minutes Expand to see summary At first, this was a really easy post to write, but then I discovered some things. Built a lot of things. Spent...

**来源信息**
- **来源**:Hacker News:AI 热帖
- **分类**:ai-products
- **发布时间**:2026-07-04 04:23(北京时间)
- **原文**:[打开原文](https://aifoc.us/influencing-model-output-with-urls)