factual

Aligning superhuman models is much harder

At current capability levels there is a pretty good set of ideas for alignment, but one should not underestimate the difficulty of aligning models that are actually smarter than us and capable of deliberately misrepresenting their intentions.

factualpending

Speaker

Ilya Sutskever

Evidence Quote

“I would not underestimate the difficulty of alignment of models that are actually smarter than us, of models that are capable of misrepresenting their intentions.”

Source

Ilya Sutskever (OpenAI Chief Scientist) — Why next-token prediction could surpass human intelligence— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:26:51 AM

Your notes

Loading notes...