# Encounter Test：用Fable模拟D&D遭遇战

- 来源：Ethan Mollick (@emollick)
- 发布时间：2026-07-06 12:20
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmr8rdjpx003vslvp63s6s899
- 原文链接：https://x.com/emollick/status/2073985468736106544

## AI 摘要

Ethan Mollick 提出“Encounter Test”作为 AI 的极客基准：让 AI 模拟两个 D&D 生物（灵吸怪 vs. 卓尔武士）对战，观察多久出错。此前测试中 GPT-4o 表现最佳，Gemini 表现有趣。不到 2 年后，借助 Fable 实现了更完整的模拟——设定初始属性、模拟每步动作（含先攻、掷骰），从 60 英尺距离开始，并以 3D 仿真展示结果。

## 正文

Less than 2 years later, with Fable: "simulate an encounter between a mind flayer and a drow warrior of equal CR. Set up initial stats then simulate each move, including initiative, rolling dice as needed, starting from 60 ft apart. Show me the results in a 3D simulation"

### 引用推文

> Ethan Mollick：I propose the Encounter Test as a nerdy benchmark standard for AI. Ask an AI to simulate an encounter between two D&D creatures & see how long it takes to mess ...