normative
Alignment must cover continuously updating weights
Current alignment research mostly addresses how frozen weights behave in deployment, but labs need new work to guarantee that a continually updated model avoids jailbreaks, deceptive or evil personas, and backdoors injected by users.
normativepending
Speaker
Dwarkesh PatelEvidence Quote
“how do you prevent users from injecting backdoors or some kind of malicious inclination into the base model?”
Source
Dwarkesh Patel Podcast - 8 Predictions for the Era of Continual Learning— Dwarkesh Patel PodcastCreated: 11/17/2026, 6:25:01 AM
Your notes
Loading notes...