Making AI trustworthy: Can we overcome black-box hallucinations?
Mike Capps
Contributor
Share on Twitter
Dr. Mike Capps is CEO and co-founder of ethical AI startup Diveplane and former president of Epic Games.
Like most engineers, as a kid I could answer elementary school math problems by just filling in the answers.
But when I didn’t “show my work,” my teachers would dock points; the right answer wasn’t worth much without an explanation. Yet, those lofty standards for explainability in long division somehow don’t seem to apply to AI systems, even those making crucial, life-impacting decisi
コメント