Simon Driscoll

Learned AI simulators can pass standard forecast metrics yet fundamentally fail to capture system dynamics, as demonstrated by a new response theory probe that reveals critical divergences in forced responses.

AI's role in exacerbating environmental harm is often overlooked, yet it can significantly undermine sustainability efforts across various sectors.

Significant architectural differences in machine learning models only emerge during active sudden stratospheric warming events, revealing the crucial role of vertical coupling in accurate predictions.