Even the scientists who build AI can’t tell you how it works

 

Artificial intelligence systems like ChatGPT can do a wide range of impressive things: they can write passable essays, they can ace the bar exam, they’ve even been used for scientific research. But ask an AI researcher how it does all this, and they shrug.

“If we open up ChatGPT or a system like it and look inside, you just see millions of numbers flipping around a few hundred times a second,” says AI scientist Sam Bowman. “And we just have no idea what any of it means.”

Bowman is a professor at NYU, where he runs an AI research lab, and he’s a researcher at Anthropic, an AI research company. He’s spent years building systems like ChatGPT, assessing what they can do, and studying how they work. 

More Here