Jan Leike
Person on 2 sites
Alignment researcher. Co-led OpenAI's superalignment team until 2024 and has led alignment work at Anthropic since; writes Musings on the Alignment Problem.
-
2 channels on ppll (opens ppll.app)
Where public figures publish, and what they are on record saying.
Updated 2026-09-10 -
16 beliefs on korrents (opens korrents.com)
-
Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. (opens korrents.com)
“This is the hard problem of alignment we need to solve in order to succeed at building superintelligence, and to this day it is an unsolved problem.”
-
Simple training interventions turned out to be very effective at steering models towards aligned behaviour. (opens korrents.com)
“But the most important lesson is that simple interventions are very effective at steering the model towards more aligned behavior.”
-
We do not have to align superintelligence directly; we have to build a human-level automated alignment researcher we trust more than ourselves. (opens korrents.com)
“But the goal we need to achieve is so much easier: we just need to build a model that’s as good as us at alignment research, and that we trust more than ourselves to do this research well because it’s sufficiently…”
-
Alignment of today's models is going well enough to look solvable, while aligning models we can no longer understand remains unsolved. (opens korrents.com)