Friendly AI research news: FriendlyAI.tumblr.com

post by lukeprog · 2011-09-18T19:08:54.975Z · LW · GW · Legacy · 20 comments

Contents

20 comments

I will be posting news on Friendly AI research here: FriendlyAI.tumblr.com. Follow the link to stay tuned via Tumblr or RSS.

20 comments

Comments sorted by top scores.

comment by Alexei · 2011-09-18T19:29:25.967Z · LW(p) · GW(p)

I'm not sure how I feel about the images used on that website. I feel that they trigger all the wrong associations. Digital-looking human-like hand just reinforces the assumption that the AI will be human-like, and the robot head brings to mind all the recent AI movies.

Replies from: lukeprog
comment by lukeprog · 2011-09-18T19:32:28.814Z · LW(p) · GW(p)

If you can come up with better images to represent Friendly AI, please let me know!

EDIT: How 'bout now?

Replies from: nhamann, Hyena, Alexei
comment by nhamann · 2011-09-19T17:58:00.797Z · LW(p) · GW(p)

If you can come up with better images to represent Friendly AI, please let me know!

How about an image of a paper clip?

Replies from: JoshuaZ
comment by JoshuaZ · 2011-09-19T18:23:06.189Z · LW(p) · GW(p)

That seems to be too much like an image that will only appeal to people who are already familiar not only with the ideas of FAI but with specific variants that are discussed only on LW. For most people that will probably be confusing.

Replies from: AlexSchell, pedanterrific
comment by AlexSchell · 2011-09-19T23:59:01.227Z · LW(p) · GW(p)

A similar specific variant: http://s.wsj.net/public/resources/images/OB-DU671_0604dn_D_20090604122543.jpg

Replies from: pedanterrific
comment by pedanterrific · 2011-09-20T00:31:26.361Z · LW(p) · GW(p)

Man, we're never gonna let Hibbard forget that, are we? You propose one obviously-flawed genocidal AI Overlord...

Replies from: JoshuaZ
comment by JoshuaZ · 2011-09-20T02:41:26.773Z · LW(p) · GW(p)

Sorry, did he ever actually propose a smiley tiler? I thought that was just used as an example of a simple way one could easily go wrong.

Replies from: pedanterrific
comment by pedanterrific · 2011-09-20T02:49:07.289Z · LW(p) · GW(p)

Well, he sort of did, actually.

Replies from: JoshuaZ
comment by JoshuaZ · 2011-09-20T02:56:39.622Z · LW(p) · GW(p)

That's just... wow. That's frighteningly stupid. That's about as bad as someone saying they aren't worried about a nuclear reactor undergoing a meltdown because they had their local clergy bless it although the potential negative pay off of this is orders of magnitude higher. I don't put a high probability to an AI triggered singularity but this is just... wow. One thing seems pretty clear: if an AGI does do a hard-take off to control its light cone, the result is likely to be really bad, simply because so many people are being stupid about it.

Part of me is worried that the SIAI people are thinking much more carefully about some of these issues maybe should suggest that their estimates for recursively self-improving are much more likely than I estimate.

Replies from: pedanterrific
comment by pedanterrific · 2011-09-20T03:11:47.709Z · LW(p) · GW(p)

To me, the frightening thing isn't the original mistake (though it is egregious), it's the fact that the response to having it pointed out was "You should not assume such a poor implementation of my idea that it cannot make discriminations that are trivial to current humans" rather than "OOPS!"

comment by pedanterrific · 2011-09-19T18:38:14.808Z · LW(p) · GW(p)

Plus there's the people who'll go "friendly" + "AI" + "paperclip" = "Microsoft Word help menu interface" and feel a surge of irrational hatred.

Replies from: Vladimir_Nesov
comment by Vladimir_Nesov · 2011-09-19T20:38:27.259Z · LW(p) · GW(p)

... "Microsoft Word help menu interface" and feel a surge of irrational hatred.

I think in this case the Way affirms one's hatred.

Replies from: pedanterrific
comment by pedanterrific · 2011-09-20T00:28:55.405Z · LW(p) · GW(p)

You're probably right. Replace "irrational" with "misplaced", maybe.

(Also, I owe Clippy an apology for bringing up the Great Shame of paperclip enthusiasts everywhere.)

comment by Hyena · 2011-09-18T21:55:49.769Z · LW(p) · GW(p)

The current image looks like Vacuum Doomsday. What about no image, just calming or neutral tones?

Replies from: lukeprog
comment by lukeprog · 2011-09-19T05:38:47.552Z · LW(p) · GW(p)

What is Vacuum Doomsday?

Replies from: Hyena
comment by Hyena · 2011-09-19T20:56:27.520Z · LW(p) · GW(p)

It looked like everything in the picture was being sucked into space, perhaps by an enormous robotic maid.

comment by Alexei · 2011-09-18T21:31:23.454Z · LW(p) · GW(p)

Yeah, that looks fine, although I'm not sure what it is.

As for FAI images, I think most math-related images (equations, etc...) are fine. Abstract diagrams, trees, graphs, etc...

Replies from: pedanterrific
comment by pedanterrific · 2011-09-18T21:48:34.920Z · LW(p) · GW(p)

Inside view of a toroidal space habitat, is what I assumed.

I'd suggest some kind of Matrix-style 'wireframe made of equations' thing as being probably the best illustration, except for the obvious negative connotations.

Replies from: lukeprog
comment by lukeprog · 2011-09-18T23:16:36.999Z · LW(p) · GW(p)

Inside view of a toroidal space habitat, is what I assumed.

Yes. Specifically, I think it's meant to be the inside of a Stanford torus.

comment by alexvermeer · 2011-09-19T15:37:35.234Z · LW(p) · GW(p)

RSS'd. Thanks.