John Silliphant

What if much of AI alignment work today is resting on an under-examined assumption that’s been hiding in plain sight? Most alignment approaches draw a boundary between what the system is optimizing for and what it regards as context. The concern is that this “context” may turn out to include...

Dear LessWrong community, Back in 1992, AI was still in its infancy. The world was dangerously out of alignment then, too, and I wondered at that time what could be done about it. In a conversation, a friend and I locked into a simple but powerful contradiction: how can we...