DeepMind 发布 Genie 4，可搭配 Gemini 3.8 Flash 分步验证任务
DeepMind 的 Genie 4 来了，能配 Gemini 3.8 Flash 看场景拆步骤、逐步检查，还能模拟 Apollo 人形机器人，做机器人训练的值得看。
DeepMind 发布 Genie 4 世界模型。Gemini 3.8 Flash 可观察 Genie 4 生成的场景，把任务拆成步骤并逐步检查执行结果，场景变化时同步更新计划。DeepMind 还展示了 Gemini 4 Argon 与 Genie 4 模拟 Apollo 人形机器人下跳棋的实验。对机器人领域而言，这套组合可用于测试任务中途移动物体后，智能体能否通过重新规划完成恢复。
The long awaited Genie 4 is here!
Gemini 3.8 Flash watches the generated scene, breaks a task into steps and checks whether each step worked. As the scene changes, it updates its plan. DeepMind also shows an experiment with Gemini 4 Argon and Genie 4 simulating an Apollo humanoid playing checkers.
This is of course a particularly big leap for robotics, which needs world models. Genie 4 + Gemini could provide a place to do that: move an object mid-task, let Gemini replan, and see whether the agent recovers.
Well done @GoogleDeepMind !
