@TheINAOG

中文参考

最后我访问了@typesafeai（谢谢你们！） Jev +模拟器前瞻性清除《超级马里奥兄弟》1-1仅需0.04美元。 在这个设置中，Jev看不到像素：我将RAM解析为结构化状态、模拟控制器宏、过滤预测死亡，然后让Jev选择。已记录运行; API中断后从同一状态恢复。 权衡：RAM提供精确、可审计的观察，但我的适配器是特定于游戏的。回避视觉使这个实验变得更容易;它不能解决一般游戏代理的感知问题。 Jev的潜力是作为结构化观察和预测结果的战术决策层。 警告：1-1对于RAM +搜索很容易。接下来：Jev与相同模拟上的廉价启发式。该模型真的赢得了自己的地位吗？

原帖全文 / EN

Finally I got access to @typesafeai (thank you guys!) Jev + emulator lookahead cleared Super Mario Bros. 1-1 only 0.04$. In this setup, Jev sees no pixels: I parsed RAM into structured state, simulated controller macros, filtered predicted deaths, and let Jev choose. Recorded the run; resumed from the same state after an API outage. The tradeoff: RAM gives precise, auditable observations, but my adapter is game-specific. Bypassing vision makes this experiment easier; it doesn’t solve perception for general game agents. The potential is Jev as a tactical decision layer over structured observations and predicted outcomes. Caveat: 1-1 is easy for RAM + search. Next: Jev vs a cheap heuristic on identical simulations. Does the model actually earn its place?