‘Unlearning’ shows promise in curbing dangerous AI use

Researchers hope their work training AI to forget some things it’s learned will prevent it from building weapons of mass destruction., (NewsNation) — How do we know if an artificial intelligence system is producing “hazardous knowledge”? And if it does, what do we do about it? The answers may be in a fairly new AI concept called “unlearning.” Dozens of AI researchers have come up with the “Weapons of Mass Destruction Proxy,” a collection of 4,157 multiple-choice questions. The answers could help determine whether an AI model might be used in,

from Newsnation

Read More