Take this example: a Microsoft team is just now figuring out how to use a diffusion model to find new materials that can fit the bill for high-tech projects.

The model, called ether0, outperforms other advanced AIs at chemistry tasks and is a stepping stone towards automating the entire research pipeline.

Unlike models such as Google’s Neural GCM, which is trained on the same weather data as today’s top climate models, emulators are typically trained on the outputs of full-scale climate models.