normative
Alignment confidence must scale with capability
The more capable a model is, the more confident you need to be before releasing it, and you want to be in a world where the degree of alignment keeps increasing faster than the capability of the models.
normativepending
Speaker
Ilya SutskeverEvidence Quote
“you also want to be in a world where your degree of alignment keeps increasing faster than the capability of the models.”
Source
Ilya Sutskever (OpenAI Chief Scientist) — Why next-token prediction could surpass human intelligence— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:26:51 AM
My Notes
Loading notes...