normative
Interpretability-based training could steer AI thinking directly
A promising route is to understand models well enough to train them on how they think, not just what they do, intervening directly on internal reasoning about reward and hacking to prevent bad behavior.
normativepending
Speaker
Paul ChristianoEvidence Quote
“You could try and say, ‘We’re going to understand really well how models work internally, and then we can train them based not just on what they do, but on how they think.’”
Source
Dwarkesh Patel Podcast - Paul Christiano – We could be 12 months away from AIs that can overthrow the government— Dwarkesh Patel PodcastCreated: 11/17/2026, 6:22:08 AM
Your notes
Loading notes...