AI is not very good at predicting what happens next when objects interact
Bear at al. Stanford University/UC San Diego/MIT
Artificial intelligence struggles to comprehend how objects interact with each other as they roll, collide, drop and drape, flunking a set of benchmark tests designed to see how intelligent it really is.
The so-called Physion benchmark was designed by Daniel Bear at Stanford University in California and his colleagues. It uses eight scenarios to showcase physical phenomena most humans understand innately.
AIs were given the opening moments of the scenarios, computer-generated in 3D, featuring objects that were designed …
More Stories
Fish can recognize themselves in photos, further evidence they may be self-aware
Robotic hand pokes food and water to tell if they have mercury in them
AI image generators that create close copies could be a legal headache