Claude Code and Fable 5 ported the 2003 PC game Command & Conquer to native iOS in "a few hours"
Quick Answer
Ammaar Reshi from Google DeepMind successfully ported 'Command & Conquer: Generals Zero Hour' to iOS using Anthropic's Claude Code and Fable 5, completing the initial build in 40 minutes and debugging in a few hours.
Quick Take
The game runs natively on ARM64 without an emulator, but users need their own copy from Steam to play.
Key Points
- Game runs natively on ARM64 with touch controls for campaign and skirmish modes.
- Initial build took 40 minutes, followed by a few hours of debugging.
- Reshi published the source code on GitHub; game assets are not included.
- High memory usage may cause crashes on iPads during long sessions.
- Engineering log documents all bugs and fixes encountered during development.
📖 Reader Mode
~1 min readA Google Deepmind developer ported "Command & Conquer: Generals Zero Hour" to iPhone and iPad. Ammaar Reshi, Lead Product and Design for Google AI Studio, used Anthropic's Claude Code with Fable 5. The 2003 real-time strategy game runs natively on ARM64 with no emulator. Campaign, skirmish, and "Generals Challenge" all work with touch controls. The graphics pipeline translates DirectX 8 to Apple's Metal API through several intermediate steps.
Reshi says the first build took about 40 minutes, followed by "a few hours" of debugging. Over two days, Reshi burned through his entire Claude Max quota. When asked why he used a competitor's product, Reshi replied that "you can love the AI space and respect the competition while still being fully focused on building the best answer. It’s a long game."
Reshi published the full source code on GitHub as open source. Game assets aren't included, so you need your own copy, available on Steam for about $5, if you want to try it out. On iPads, the game can crash during long sessions because of high memory usage. An engineering log documents every bug and fix.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
