Large language models can do jaw-dropping things. But nobody knows exactly why.

Despite all their runaway success, nobody knows exactly how—or why—large language models work. And that’s a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

This story was written by senior AI editor Will Douglas Heaven and narrated by Noa ((News Over Audio), an app offering you professionally-read articles from the world’s best publications.