normative
Goal of training methods immune to receptive failures
The aim of Christiano's alignment research is to design training methods that don't lead to reward hacking or deceptive alignment, ideally working so well (also addressing mundane problems) that there is no 'alignment tax' and people adopt them by default, eliminating the worry about these failure modes.
normativepending
Speaker
Paul ChristianoEvidence Quote
“Ideally those methods would just work quite well and so people would be like, sure, I mean, they also address a bunch of other more mundane problems so why would we not use them?”
Created: 6/13/2026, 3:36:05 AM
Your notes
Loading notes...