He says he will be doing alignment work, the worst thing I can think of that can realistically happen is that he gives OpenAI unwarranted confidence in how aligned their AIs are. Working at OpenAI isn’t intrinsically bad, publishing capabilities research is.
He says he will be doing alignment work, the worst thing I can think of that can realistically happen is that he gives OpenAI unwarranted confidence in how aligned their AIs are. Working at OpenAI isn’t intrinsically bad, publishing capabilities research is.