The claim that AI capabilities research is bad for Alignment is non-obvious.
In particular, if you think of AI-Alignment as a race between knowledge and hardware (more knowledge makes aligning AI easier, more hardware makes building dangerous AI easier), then AI research (that isn’t purely building faster hardware) is net-positive.
The claim that AI capabilities research is bad for Alignment is non-obvious.
In particular, if you think of AI-Alignment as a race between knowledge and hardware (more knowledge makes aligning AI easier, more hardware makes building dangerous AI easier), then AI research (that isn’t purely building faster hardware) is net-positive.
I have never thought of such a race. I think this comment is worth its own post.
The link is the post where I recently encountered the idea.