The Download: training robots with gen AI, and the state of climate tech

Generative AI models can produce images in response to prompts within seconds, and they've recently been used for everything from highlighting their own inherent bias to preserving precious memories. Now, researchers from Stephen James's Robot Learning Lab in London are using image-generating AI models for a new purpose: creating training data for robots. They've developed a new system, called Genima, that fine-tunes the image-generating AI model Stable Diffusion to draw robots' movements, helping guide them both in simulations and in the real world. Genima could make it easier to train different types of robots to complete tasks--machines ranging from mechanical arms to humanoid robots and driverless cars--as well as making AI web agents more useful. We've just unveiled our 2024 list of 15 Climate Tech Companies to Watch.