factual
We Cannot Program Human Values Into AI
The real near-term challenge is not trolley problems but that we cannot program basic values like 'do no harm' into current AI, because the image-recognition learning model fails for abstract concepts—you cannot show pictures of harm to teach what harm is—and we lack ways to specify values in terms learning systems understand, as DeepMind's team found when they came up dry.
factualpending
Speaker
Gary MarcusEvidence Quote
“we just don't know how to program what harm is, we don't know how to program really any human values into current technology”
Created: 6/13/2026, 12:27:05 AM
Your notes
Loading notes...