mindviews

Karma: 81

mindviews Jun 24, 2010, 1:45 AM
2 points
on: A Rational Education
I got an amazing amount of use out of Order of Magnitude Physics. It can get you in the habit of estimating everything in terms of numbers. I’ve found that relentlessly calculating estimates greatly reduces the number of biased intuitive judgments I make. A good class will include a lot of interaction and out-loud thinking about the assumptions your estimates are based on. Also or as an alternative, a high-level engineering design course can provide many of the same experiences within the context of a particular domain. (Aerospace/architecture/transportation/economic systems can all provide good design problems for this type of thinking—oddly, I haven’t yet seen a computer science design problem example that works as well.)

Also, I’ll second recommendations for just about any psychology course. And anywhere you see a course cross-listed between psychology and economics you’ll have a good chance of learning about human bias.

mindviews Jun 22, 2010, 3:46 AM
0 points
in reply to: wedrifid’s comment on: What if AI doesn’t quite go FOOM?
So you’re positing a technique that takes advantage of inflationary theory to permanently get rid of an AI. Thermite—very practical. Launching the little AI box across the universe at near light-speed for a few billion years until inflation takes it beyond our horizon—not practical.

To bring this thread back onto the LW Highway...

It looks like you fell into a failure mode of defending what would otherwise have been a throwaway statement—probably to preserve the appearance of consistency, the desire not to be wrong in public, etc. (Do we have a list of these somewhere? I couldn’t find examples in the LW wiki.) A better response to “I hope that was a joke...” than “You are mistaken” would be “Yeah. It was hyperbole for effect.” or something along those lines.

A better initial comment from me would have been to make it into an actual question because I thought you might have had a genuine misunderstanding about light cones and world lines. Instead, it came off hostile which wasn’t what I intended.

mindviews Jun 21, 2010, 8:56 AM
0 points
in reply to: wedrifid’s comment on: What if AI doesn’t quite go FOOM?
I’m pretty sure I’m not mistaken. At this risk of driving this sidetrack off a cliff...

Once an object (in this case, a potentially dangerous AI) is in our past light cone, the only way for its world line to stay outside of our future light cone forever (besides terminating it through thermite destruction as mentioned above) is for it to travel at the speed of light or faster. That was the physics nitpick I was making. In short, destroy it because you cannot send it far enough away fast enough to keep it from coming back and eating us.

mindviews Jun 21, 2010, 8:16 AM
7 points
in reply to: SilasBarta’s comment on: Open Thread June 2010, Part 4

it’s basically saying that gravity and EM are both obeying some more general law

No, what’s happening is that under certain approximations the two are described by similar math. The trick is to know when the approximations break down and what the math actually translates to physically.

Does it suggest a way to unify gravity and EM?

No.

Keep in mind that for EM there are 2 charges while gravity has only 1. Also, like electric charges repel while like gravitic charges attract. This messes with your expectations about the sign of an interaction when you go from one to the other. That means your intuitive understanding of EM doesn’t map well to understanding gravity.

mindviews Jun 21, 2010, 7:13 AM
3 points
in reply to: wedrifid’s comment on: What if AI doesn’t quite go FOOM?

Well, I suppose you could launch them out of our future light cone.

I hope that was a joke because that doesn’t square with our current understanding of how physics works...

mindviews Jun 21, 2010, 6:58 AM
2 points
in reply to: PhilGoetz’s comment on: What if AI doesn’t quite go FOOM?

The morals of FAI theory don’t mesh well at all with the morals of transhumanism.

It’s not clear to me that a “transhuman” AI would have the same properties as a “synthetic” AI. I’m assuming that a transhuman AI would be based on scanning in a human brain and then running a simulation of the brain while a synthetic AI would be more declaratively algorithmic. In that scenario, proving a self-modification would be an improvement for a transhuman AI would be much more difficult so I would treat it differently. Because of that, I’d expect a transhuman AI to be orders of magnitude slower to adapt and thus less dangerous than a synthetic AI. For that reason, I think it is reasonable to treat the two classes differently.

mindviews Jun 14, 2010, 11:04 AM
1 point
in reply to: Yoreth’s comment on: Open Thread June 2010, Part 3

Of course, it could just add complexity and hope that it works, but that’s just evolution, not intelligence explosion.

The critical aspect of a “major-impact intelligence-explosion singularity” isn’t the method for improvement but the rate of improvement. If computer processing power continues to grow at an exponential rate, even an inefficiently improving AI will have the growth in raw computing power behind it.

So: do you know any counterarguments or articles that address either of these points?

I don’t have any articles but I’ll take a stab at counterarguments.

A Majoritarian counterargument: AI turned out to be harder and further away than originally thought. The general view is still tempered by the failure of AI to live up to those expectations. In short, the AI researchers cried “wolf!” too much 30 years ago and now their predictions aren’t given much weight because of that bad track record.

A mind can’t understand itself counterargument: Even accepting as a premise that a mind can’t completely understand itself, that’s not an argument that it can’t understand itself better than it currently does. The question then becomes which parts of the AI mind are important for reasoning/intelligence and can an AI understand and improve that capability at a faster rate than humans.

mindviews May 31, 2010, 2:40 AM
3 points
in reply to: gwern’s comment on: Diseased thinking: dissolving questions about disease
I don’t think that’s a good example. For the status-quo bias to be at work we need to have the case that we think it’s worse for people to have both less personal responsibility and more personal responsibility (i.e., the status-quo is a local optimum). I’m not sure anyone would argue that having more personal responsibility is bad, so the status-quo bias wouldn’t be in play and the preference reversal test wouldn’t apply. (A similar argument works for the current rate of heroin addiction not being a local optimum.)

I think the problem in the example is that it mixes the axes for our preferences for people to have personal responsibility and our preferences for people not to be addicted to heroin. So we have a space with at least these two dimensions. But I’ll claim that personal responsibility and heroin use are not orthagonal.

I think the real argument is in the coupling between personal responsibility and heroin addiction. Should we have more coupling or less coupling? The drug in this example would make for less coupling. So let’s do a preference reversal test and see if we had a drug that made your chances of heroin addiction more coupled to your personal responsiblity, would you take that? I think that would be a valid preference reversal test in this case if you think the current coupling is a local optimum.

mindviews May 17, 2010, 8:18 AM
1 point
on: Preface to a Proposal for a New Mode of Inquiry
Thoughts I found interesting:

The failures indicate that, instead of being threads in a majestic general theory, the successes were just narrow, isolated solutions to problems that turned out to be easier than they originally appeared.

Interesting because I don’t think it’s true. I think the problem is more about the need of AI builders to show results. Providing a solution (or a partial solution or a path to a solution) in a narrow context is a way to do that when your tools aren’t yet powerful enough for more general or mixed approaches. Given the variety of identifiable structures in the human brain that gives us intelligence I strongly expect that an AI will be built by combining many specialized parts that will probably be based on multiple research areas we’d recognize today.

One obvious influence comes from computer science, since presumably AI will eventually be built using software. But this fact appears irrelevant to me, and so the influence of computer science on AI seems like a disastrous historical accident.

Interesting because it forced me to consider what I think AI is outside the context of computer science—something I don’t normally do.

In my view, AI can and must become a hard, empirical science, in which researchers propose, test, refine, and often discard theories of empirical reality.

Interesting because I’m very curious to see what this means in the context of your coming proposal.

mindviews May 16, 2010, 8:15 AM
5 points
on: Attention Lurkers: Please say hi
Hi all—been lurking since LW started and followed Overcoming Bias before that, too.