Comment by Riteofwhey on Steelmaning AI risk critiques · 2015-07-25T08:09:00.595Z · LW · GW

I would be somewhat more convinced that MIRI was up to it's mission if they could contribute to much simpler problems in prerequisite fields.

Comment by Riteofwhey on Steelmaning AI risk critiques · 2015-07-24T15:36:06.463Z · LW · GW

Verification seems like a strictly simpler problem. If we can't prove properties for a web server, how are we going to do anything about a completely unspecified AI?

The AI take over scenarios I've head almost always involve some kind of hacking, because today hacking is easy. I don't see why that would necessarily be the case a decade from now. We could prove some operating system security guarantees for instance.

Comment by Riteofwhey on Steelmaning AI risk critiques · 2015-07-24T02:47:37.626Z · LW · GW

Thanks for doing this. A lack of self criticism about AI risk is one of the reasons I don't take it too seriously.

I generally agree with http://su3su2u1.tumblr.com/ , but it may not be organized enough to be helpful.

As for MIRI specifically, I think you'd be much better served by mainstream software verification and cryptography research. I've never seen anyone address why that is not the case.

I have a bunch of disorganized notes about why I'm not convinced of AI risk, if you're interested I could share more.