Comments on: Distrusting Drama http://www.overcomingbias.com/2008/12/types-of-distru.html Overcoming Bias is economist Robin Hanson’s blog, on honesty, signaling, disagreement, forecasting, and the far future. Sat, 11 Feb 2012 23:23:58 +0000 hourly 1 http://wordpress.org/?v=3.1.3 By: Phil Goetz http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390337 Phil Goetz Tue, 16 Dec 2008 23:29:49 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390337 Eliezer: "Thou shalt give me examples." Put this in a google search box: site:overcomingbias.com "and lo" site:overcomingbias.com "unto" I'll retract the qualifier "when speaking of himself", which I used because the examples I remembered were from the recent string of autobiographical posts. It seems to be a general inclination to use occasional archaic words. Eliezer: “Thou shalt give me examples.”

Put this in a google search box:
site:overcomingbias.com “and lo”
site:overcomingbias.com “unto”

I’ll retract the qualifier “when speaking of himself”, which I used because the examples I remembered were from the recent string of autobiographical posts. It seems to be a general inclination to use occasional archaic words.

]]> By: scholar http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390336 scholar Tue, 16 Dec 2008 03:39:57 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390336 @Phil <em>Berashith Bera Eliezer Ath Ha Amudi Va Ath Ha AI</em>. In the beginning Eliezer Created the Friendly and the AI. <em>Viamr Eliezer Ihi AI Vihi AI</em>. And said Eliezer Let there be AI, and there was AI. -- Overcoming Genesis, 1:1, 1:3, The AI Testament (^.^) @Phil

Berashith Bera Eliezer Ath Ha Amudi Va Ath Ha AI.
In the beginning Eliezer Created the Friendly and the AI.

Viamr Eliezer Ihi AI Vihi AI.
And said Eliezer Let there be AI, and there was AI.

– Overcoming Genesis, 1:1, 1:3, The AI Testament (^.^)

]]> By: Mike Blume http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390335 Mike Blume Tue, 16 Dec 2008 03:05:51 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390335 Ok, that makes more sense, it just seems to me like you run into massive <a href = "http://www.overcomingbias.com/2007/11/complex-wishes.html" rel="nofollow">wishing problems</a> when you try to formulate the phrase "when you pull me apart for carbon atoms" Ok, that makes more sense, it just seems to me like you run into massive wishing problems when you try to formulate the phrase “when you pull me apart for carbon atoms”

]]> By: burger flipper http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390334 burger flipper Tue, 16 Dec 2008 02:48:30 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390334 Mike Blume, I'm simply proposing an ad hoc stipulation be built in at go: when you pull me apart for the carbon atoms, plunk down a sim of me in the ant farm. Instead of us building an escape proof box for it, let it build one for us. Not ideal perhaps. But if the first AI is likely to take over, the world's leading proponent of friendly AI is in the providing-inspiration-for-the-young'ins stage, and copies/uploads/simulations of a person are that person, it seems like the best bet. And then EY can redirect his efforts toward creating the first AI--friendly or not. Mike Blume, I’m simply proposing an ad hoc stipulation be built in at go: when you pull me apart for the carbon atoms, plunk down a sim of me in the ant farm. Instead of us building an escape proof box for it, let it build one for us.

Not ideal perhaps. But if the first AI is likely to take over, the world’s leading proponent of friendly AI is in the providing-inspiration-for-the-young’ins stage, and copies/uploads/simulations of a person are that person, it seems like the best bet.

And then EY can redirect his efforts toward creating the first AI–friendly or not.

]]> By: Eliezer Yudkowsky http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390333 Eliezer Yudkowsky Tue, 16 Dec 2008 02:10:20 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390333 <blockquote>I mean, sometimes he uses King James Version grammar when speaking of himself.</blockquote> Not that I think that's a bad thing, but still, I'm not entirely sure what you're talking about here. Thou shalt give me examples.

I mean, sometimes he uses King James Version grammar when speaking of himself.

Not that I think that’s a bad thing, but still, I’m not entirely sure what you’re talking about here. Thou shalt give me examples.

]]> By: Phil Goetz http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390332 Phil Goetz Tue, 16 Dec 2008 01:05:21 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390332 Eliezer is pretty dramatic a lot of the time. I mean, sometimes he uses King James Version grammar when speaking of himself. That's a little disturbing. However, I have often observed that, in subjective fields, people who absurdly overstate their claims, like Freud and Kuhn and Lovelock and Skinner and Derrida and most famous philosophers; or make claims that are absurd to begin with, like James Tipler and (sometimes) Jerry Fodor and most of whatever famous philosophers are left; get more attention than people like, I don't know, Spinoza, who make reasonable claims. Eliezer is pretty dramatic a lot of the time. I mean, sometimes he uses King James Version grammar when speaking of himself. That’s a little disturbing.

However, I have often observed that, in subjective fields, people who absurdly overstate their claims, like Freud and Kuhn and Lovelock and Skinner and Derrida and most famous philosophers; or make claims that are absurd to begin with, like James Tipler and (sometimes) Jerry Fodor and most of whatever famous philosophers are left; get more attention than people like, I don’t know, Spinoza, who make reasonable claims.

]]> By: Mike Blume http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390331 Mike Blume Tue, 16 Dec 2008 00:10:48 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390331 burger flipper: <i>trade?</i> If I choose to keep a set of ants in a glass sandbox on my desk, I do it because it amuses me. There is <i>absolutely nothing</i> those ants could <i>hope</i> to offer me which would make one iota of difference in the matter, and indeed, which I could not take from them myself. What on earth could we <i>possibly</i> trade with an unfriendly AI? burger flipper: trade?

If I choose to keep a set of ants in a glass sandbox on my desk, I do it because it amuses me. There is absolutely nothing those ants could hope to offer me which would make one iota of difference in the matter, and indeed, which I could not take from them myself.

What on earth could we possibly trade with an unfriendly AI?

]]> By: burger flipper http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390330 burger flipper Mon, 15 Dec 2008 19:46:15 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390330 If fooming AI is an eventuality and the cutting edge of friendly technology consists of inspiring the next generation, it might be time for a contingency plan. If the AI is going to be so powerful it cannot be contained in any box, if it could use human atoms for building blocks, and if simulated me=me; maybe we should trade the atoms for a box, one to be placed in ourselves: simulations given a simulated earth. We don't even have to swallow the blue pill. Leave the memories so we either don't build another AI within the AI simulation, or if we do build one, leave the memory of the solution intact so we just live in a recursive loop. If fooming AI is an eventuality and the cutting edge of friendly technology consists of inspiring the next generation, it might be time for a contingency plan.

If the AI is going to be so powerful it cannot be contained in any box, if it could use human atoms for building blocks, and if simulated me=me; maybe we should trade the atoms for a box, one to be placed in ourselves: simulations given a simulated earth. We don’t even have to swallow the blue pill. Leave the memories so we either don’t build another AI within the AI simulation, or if we do build one, leave the memory of the solution intact so we just live in a recursive loop.

]]> By: Z. M. Davis http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390329 Z. M. Davis Mon, 15 Dec 2008 18:19:36 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390329 Burger flipper: <i>"That leaves tricky questions about setting the rules of the sand box we get plunked down in. But would the sandbox rules need to be as perfect as the AI's utility function?"</i> <i><a href="http://www.overcomingbias.com/2008/08/dreams-of-frien.html" rel="nofollow">Yes</a>.</i> Burger flipper: “That leaves tricky questions about setting the rules of the sand box we get plunked down in. But would the sandbox rules need to be as perfect as the AI’s utility function?”

Yes.

]]> By: James Andrix http://www.overcomingbias.com/2008/12/types-of-distru.html#comment-390328 James Andrix Mon, 15 Dec 2008 18:10:58 +0000 http://prod.ob.trike.com.au/2008/12/distrusting-drama.html#comment-390328 Eliezer: But the question is: Where does ROBIN think Robin's abstractions break down? He thinks he's accounted for your scenario, but he probably doesn't think his abstractions are perfect. It should be a strong argument if you can show that your foom is in one of the regions where his abstractions break, but first he should concede those regions. Eliezer:
But the question is: Where does ROBIN think Robin’s abstractions break down? He thinks he’s accounted for your scenario, but he probably doesn’t think his abstractions are perfect. It should be a strong argument if you can show that your foom is in one of the regions where his abstractions break, but first he should concede those regions.

]]>