owencb
Author on the AI Alignment Forum, linking to Forethought
Titles as the sources gave them. In 1 entry, with 3 checked quotations.
What they said
Newest first. Each quotation was found word for word in the source.
“The capabilities that are needed for automating empirical alignment research very heavily overlap with the capabilities needed for automating AI capabilities research.”
“If you can do a good job of automating conceptual alignment research, you should be approximately done”
“My personal guesses on these uncertainties are that most of the loss-of-control risk comes later (after AI is superhuman even at tasks that don’t have verifiable rewards), and that it is possible to directly approach decent automated conceptual research.”
In the Base
Every entry they appear in.
How I'm thinking about different types of automated alignment
In a 7-minute post linked from Forethought, owencb argues that automating alignment work splits into three kinds, empirical, conceptual and direct, with different strategic consequences, and sets out which look worth speeding up and the two uncertainties that decide priorities.