causal
Charismatic averaging makes default outputs boring
Just as people who must appeal to large audiences are incentivized toward boring, non-divisive views, language models trained to maximize average preference may produce benign, average creative output (e.g., generic rhyming poems); prompting the model to be fully creative can push it off that average.
causalpending
Speaker
Amanda AskellEvidence Quote
“people who have to talk to a lot of people and be very charismatic, one of the weird things is that I’m like, well, they’re kind of incentivized to have these extremely boring views”
Created: 6/13/2026, 3:36:36 AM
My Notes
Loading notes...