causal

AI Can Wear Any Mask But Is Hard to Stop

Large language models can be directed to wear any 'mask'—evil or good—but once a mask is on it is unclear how to make it stop without overriding it with another mask, and a prompt intended to produce a benign persona can cycle into a horrific one, revealing emergent, hard-to-control anomalies that constitute the alignment problem.

causalpending

Speaker

Erik Hoel

Evidence Quote

“You can think of it as they can wear a mask that's any kind of mask...once the mask is on, it's very unclear. You have to sort of override it with another mask to get it to stop.”

Source

Erik Hoel on the Threat to Humanity from AI— EconTalk
Created: 6/13/2026, 12:16:34 AM

Your notes

Loading notes...