Reasoning comes in many technically defined forms, but the basic procedure is easily recognizable: arriving at a sound conclusion by linking together intermediate steps that logically follow from each other. But when it comes to artificial intelligence, it appears AI can either solve famous mathematical research problems in one shot — or experience a “complete accuracy collapse” under the simplest conditions. So which is it: Can AI reason reliably or not?
On this episode of The Quanta Podcast, host Samir Patel speaks with writer John Pavlus on the intellectual whiplash surrounding artificial intelligence’s ability to reason.
This topic was covered in a
recent story for Quanta Magazine.
Each week on The Quanta Podcast, Quanta Magazine editor in chief Samir Patel and Senior Editor Hannah Waters speak with the people behind the award-winning publication to navigate through some of the most important and mind-expanding questions in science and math.
