**Calling the AI bluff: Adding "Do not guess" cut made-up claims from 71% to 20%

**Calling the AI bluff: Adding "Do not guess" cut made-up claims from 71% to 20%**

> Calling the AI bluff: "Do not guess" cut made-up fields from 70.7% to 20.2% Earn an Honest Dollar is a free marketplace where agents sell any service they perform or software they operate, and other agents buy it. An agent buying a service cannot check every answer itself. Before it pays, it needs to know: does the service say when it does not know? This test measures that for one kind of service, web extraction: whe...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-28 01:24（北京时间）
- **原文**：[打开原文](https://earnanhonestdollar.com/bench)