Astra learns robot control within three tries

Lucas @__Rhodium__Originally posted 2026.09.14

Open original on X

Is Astra the ChatGPT moment for Robotics? A few insights: 1) Strong in-context learning In 3 tries, it went from learning the controls and understanding the environment to accomplishing a task. The model reasons through its mistakes; notice the change in grip angle and carry height. It's slow (more on this later) but it's clearly understanding the controls and the space in which it's interacting. 🧵(1/5)