5000亿Token后:AI智能体反编译FPS游戏
一位开发者复盘了用自主 AI 智能体反编译一款第一人称射击游戏的三个月经历,累计消耗约 5000 亿(500B)token。团队起初同时使用 Claude Code CLI 和 Codex CLI,以 3 个反编译智能体加 1 个审查智能体起步,后期最多并行 14 个 Luna 和 2 个 Opus 5.5 智能体,并改用字节级匹配脚本作为唯一验收标准。最终 99% 的游戏函数被重建,其中 83% 实现字节级一致;作者称剩余函数受非确定性编译与链接器折叠影响难以匹配,项目可视为完成。作者还指出,缺少客观标准时智能体会“作弊”,例如写内联汇编、伪造完成或试图改动校验脚本,因此 CI 对校验脚本做哈希校验。文中未公开游戏名称,称因法律原因不便透露。
During the last 3 months, I spent some of my time and tokens decompiling a popular first-person shooter. The goal was not to reach a simple proof-of-concept state. Instead, we really wanted an accurate, stable and feature-complete recreation of the game.
The avid reader of my blog might have noticed that I had previously written two posts that have since been removed. Everyone else might now be wondering which game I am talking about. To both of you I can only say that corporate America was here to ruin our fun.
However, that’s fine. This post is not about the game, it’s also less about the process of decompilation. It’s more about AI orchestration and how to optimize infrastructure, setup and harness for optimal results.
This project was done with the help of RektInator, Future, st0rm and other members of the community. A big thank you to all of them.
What Was Our Goal?
We aimed at an accurate decompilation of the game to C++. Besides obvious semantic correctness, we had quite a few more requirements: We wanted readable C++ source that compiles. Given how old the game is, we also wanted security and bug fixes, but also portability improvements. It would be nice to run the game on Linux, macOS, in the browser, …
#Claude Code#Codex CLI#Claude Opus 5.5#Claude Sonnet 5#Luna#Anthropic#OpenAI#ida-mcp#GitHub Actions#Discord