The new AI model, WeatherNext 2, can generate forecasts eight times faster than Google’s previous model, and is also more accurate in predicting 99.9 percent of variables like temperature or wind. WeatherNext 2 can pump out hundreds of potential outcomes from a particular starting point. It takes less than a minute using one of Google’s TPU chips to make a prediction, which the company says would typically take several hours to accomplish using physics-based models on a supercomputer.

Google updates its weather forecasts with a new AI model | The Verge

I want to be clear - this is not a traditional LLM. However, this is personally one of the most exciting and useful applications for highly advanced machine learning models. weather modeling has not changed since the physics simulation models that are currently employed across the world. I am genuinely excited for both more accurate local prediction and for what this spurs in additional research into the field.