---
title: "用 Codex + GPT-5.6 Sol Ultra 一次生成浣熊劫案游戏：结果远超 Claude Fable 5"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Aug/7/moonlight-mayhem/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_18e9715f563cefab712bce59"
published: "2026-08-07T19:18:09.000Z"
score: 70
channel: "ai"
tags: ["Claude Fable 5","GPT-5.6 Sol Ultra","OpenAI Codex","游戏设计","生成式 AI","编码智能体"]
---

# 用 Codex + GPT-5.6 Sol Ultra 一次生成浣熊劫案游戏：结果远超 Claude Fable 5

## AI 点评

> 这类'同一提示词、不同智能体'的对照实验，比厂商演示更能反映实际开发中的体验差异。如果你正在挑选编码智能体或规划多智能体工作流，这组结果值得认真看；特别是 Sol 的子代理模式在复杂游戏生成中的表现，以及它没能在截图检查中发现视觉瑕疵这一点，都是重要的能力边界信号。

## 速览

Simon Willison 用完全相同的提示词测试 Codex Desktop 上的 GPT-5.6 Sol Ultra（激进子代理模式），要求其基于四年前 GPT-3 生成的游戏概念制作一款完整游戏。生成的《Moonlight & Mayhem》让玩家控制浣熊在博物馆中营救队友、叠罗汉夺取金沙丁鱼，比 Claude Fable 5 的版本更贴合原设定。虽然初版存在浣熊眼球异常放大的 bug，但通过简单提示即修复。整个生成过程耗时 52 分钟，Codex 还同步生成了纹理和素材。

## 关键点

- Codex Desktop + GPT-5.6 Sol Ultra 在相同提示下生成了明显更精良的抢劫主题游戏《Moonlight & Mayhem》
- 游戏设定从'后院捡硬币'升级为'营救同伴、叠罗汉偷金沙丁鱼'，更忠实于原始 Raccoon Heist 概念
- 初版存在浣熊眼球巨大化的视觉 bug，Codex 未能自动发现，但用户通过两次提示快速修复
- Codex 花费 52 分钟完成开发，并同步生成纹理与图像素材，完整转录已公开

## 全文

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5, where I had Claude Fable 5 build a full working game from a premise I generated with GPT-3 and DALL-E four years ago. I decided to pose the exact same prompt to Codex Desktop running GPT-5.6 Sol Ultra - the mode where Sol makes aggressive use of sub-agents - to see how it would do. It produced a much better game! Here's Moonlight & Mayhem - GitHub repository here, including the textures and prompts it generated using gpt-image-2. Your browser does not support HTML5 video. The original GPT-3 generated game description included: In “Raccoon Heist”, you and your team of thieving raccoons are tasked with pulling off a series of daring heists. From robbing banks to stealing priceless art, no job is too big or too small for your furry crew. Fable's version had you as a single raccoon running around a back yard collecting coins and fish. GPT-5.6 Sol has you in a museum, rescuing your two other raccoon crewmates in order to stack on top of each other and bust the golden sardine out of its case. Much more heisty! There was one catch though: the version produced from the one-shot prompt had a bug where each raccoon had an eyeball that was enlarged to the size of a giant sphere floating over their head! You can play that version here. Despite reviewing screenshots during development Codex failed to spot and correct this bug. I fixed it by prompting: Why do the raccoons have huge black spheres on them? And then: Fix it Which resulted in this fix. I shared the full Codex transcript in the repository - I wish Claude Code had the same "copy as Markdown" feature. Codex spent 52 minutes on the project. Here's the AgentsView cost estimate for that session if I had been paying full API prices as opposed to using my monthly Codex subscription: Tags: game-design, ai, openai, generative-ai, llms, coding-agents, codex, gpt

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_18e9715f563cefab712bce59