Anonymous advice: If you want to reduce AI risk, should you take roles that advance AI capabilities? (Article)
80k After Hours
00:00
AI Alignment Research Is Possible, but Only if the Team Is Very Private
Pro-social capabilities research is possible, so long as it's done strictly in private. By default, the teams that claim they will be private when it matters will happily publish a trail of breadcrumbs. But few can tell where the serial bottlenecks are, and so I think a good rule of thumb is, don't advance capabilities,. If you have to, make sure it's done in private.
Transcript
Play full episode
