opinion claim
The speaker identifies preventing users from injecting backdoors or malicious tendencies into a base model as a safety challenge if AIs consolidate learning across users.
Dwarkesh Patel · 8 Predictions for the Era of Continual Learning · 7 Aug 2026
In their words
The transcript segments this claim was taken from
“And if AIs are consolidating learnings between users as well,”
“how do we prevent users from injecting backdoors or some kind of malicious inclination into the base model?”Play from 2:25Report a misattribution
85%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly