I find it kind of bizzare that people are saying that like the real AI safety argument wasn't wheather the system could understand you it was getting it to care. Like, maybe these people have always been saying that concrete problems in AI safety w

Mentions

David Krueger @DavidSKrueger · Apr 18, 2023

From Twitter

This is a good point / thread. Note that @MIRIBerkeley and @ESYudkowsky deserve credit for (purportedly) focusing on inner alignment from the beginning. The first public documentation of this I'm aware of are Alignment Forum posts from 2017, e.g.:

Tweet Apr 18, 2023

I find it kind of bizzare that people are saying that like the real AI safety argument wasn't wheather the system could understand you it was getting it to care. Like, maybe these people have always been saying that concrete problems in AI safety w

by Nathan Barnard

Recommended by 1 person

1 mention