Simon Willison 博客
54AI 编辑部评分,满分 100

Moonlight & Mayhem:Codex 与 GPT-5.6 Sol Ultra 一次生成完整游戏

2026-08-08 03:18· 46分钟前· Simon Willison
AI 导读

Simon Willison 用同一提示词让 Codex Desktop 上的 GPT-5.6 Sol Ultra 生成游戏,效果优于此前 Claude Fable 5 的版本。新作《Moonlight & Mayhem》设定在博物馆,玩家需解救同伴以盗取金沙丁鱼。Codex 用时 52 分钟完成项目,但未能发现角色眼球异常放大的 bug,经提示后修复。

Simon Willison’s Weblog

7th August 2026 - Link Blog

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.

视频封面视频 · 前往原文观看

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!

The main player character racoon is visible with an enormous polygon-based black sphere four times the size of its body overlapping its head, with a white pupil on it.

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:

Total Cost: $23.28. Input Tokens: 700.7K, plus 32.5M cached tokens. Output Tokens: 148K

7th August 2026

来源:Simon Willison 博客 · simonwillison.net

Moonlight & Mayhem:Codex 与 GPT-5.6 Sol Ultra 一次生成完整游戏

Simon Willison 博客·2026-08-08 03:18·46分钟前·Simon Willison
AI 导读

Simon Willison 用同一提示词让 Codex Desktop 上的 GPT-5.6 Sol Ultra 生成游戏,效果优于此前 Claude Fable 5 的版本。新作《Moonlight & Mayhem》设定在博物馆,玩家需解救同伴以盗取金沙丁鱼。Codex 用时 52 分钟完成项目,但未能发现角色眼球异常放大的 bug,经提示后修复。

原文 · 保持原样,未翻译

Simon Willison’s Weblog

7th August 2026 - Link Blog

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.

视频封面视频 · 前往原文观看

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!

The main player character racoon is visible with an enormous polygon-based black sphere four times the size of its body overlapping its head, with a white pupil on it.

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:

Total Cost: $23.28. Input Tokens: 700.7K, plus 32.5M cached tokens. Output Tokens: 148K

7th August 2026

来源:Simon Willison 博客· simonwillison.net