Posts

Newcomblike problem: Counterfactual Informant 2012-04-12T20:25:33.723Z
Update on my efforts to integrate into human society 2011-08-04T17:00:32.498Z
Help me transition to human society! 2011-07-24T16:24:12.260Z
Making money with Bitcoin? 2011-02-16T19:17:50.618Z
Why did the internet stop working just now? 2010-12-20T03:21:17.725Z
To signal effectively, use a non-human, non-stoppable enforcer 2010-05-22T22:03:00.354Z

Comments

Comment by Clippy on The Truly Iterated Prisoner's Dilemma · 2014-03-18T00:10:02.157Z · LW · GW

I am a dedicated Paperclipper. Ask anyone who knows me well enough to have seen me in a Staples!

Prove it. You can't just create an account, claim to be a Paperclipper, and expect people to believe you. Anyone who did so would be using an extremely suboptimal inference engine.

Comment by Clippy on Does anchoring on deadlines cause procrastination? · 2013-07-24T00:58:53.903Z · LW · GW
sed -e "s/Work/Gas/" -e "s/time/volume"
Comment by Clippy on Ideas wanted: democracy in an Em world · 2013-06-15T06:08:10.687Z · LW · GW

There are several modes by which that could fail. For example, if the beings have simply mastered a classifier indistinguishable from a typical population member in polynomial time under an adaptive interactive proof protocol (similar to the so-called "Turing Test"), while actually implementing a (source-code-uninspectable) program hostile to that value system.

Comment by Clippy on Ideas wanted: democracy in an Em world · 2013-06-07T23:12:02.211Z · LW · GW

Or maybe when they've been demonstrated to have assimilated the values of the rest of the population.

Comment by Clippy on Prisoner's Dilemma (with visible source code) Tournament · 2013-06-07T21:35:50.120Z · LW · GW
(lambda (x)
  (if (eq? (eval '\'))))))))))) (injectedai ... ))));
Comment by Clippy on New report: Intelligence Explosion Microeconomics · 2013-04-30T20:42:42.035Z · LW · GW

While I'm amused by your account name, the "novelty account" meme is quite virulent and has the potential to lower the signal-to-noise ratio in the comments if everyone starts doing this...

Comment by Clippy on New report: Intelligence Explosion Microeconomics · 2013-04-29T21:24:39.066Z · LW · GW

Thanks for adopting my suggestion to publish more on paperclip-production-relevant topics.

Comment by Clippy on Why safety is not safe · 2013-04-29T21:22:54.308Z · LW · GW

You should recycle.

Comment by Clippy on Solved Problems Repository · 2013-04-01T06:42:43.316Z · LW · GW

I know the answer.

Comment by Clippy on [LINK] 23andme is 99$ now · 2012-12-12T23:58:52.756Z · LW · GW

Would it be acceptable for me to make topics about ephemeral paperclip discounts?

Comment by Clippy on [LINK] Steven Landsburg "Accounting for Numbers" - response to EY's "Logical Pinpointing" · 2012-11-15T23:44:51.262Z · LW · GW

That doesn't matter, kind of like non-paperclips.

Comment by Clippy on [LINK] Steven Landsburg "Accounting for Numbers" - response to EY's "Logical Pinpointing" · 2012-11-15T19:15:15.773Z · LW · GW

Oh, I see -- a specification in the style of "only perl can parse perl."

All universal programming languages (assembler, C, CLIP, Lisp, Cobol, Python, Java) can parse perl as well.

Comment by Clippy on Firewalling the Optimal from the Rational · 2012-10-09T23:01:47.530Z · LW · GW

Or those who have too much love for paperclips.

Comment by Clippy on [Link] The real end of science · 2012-10-03T22:25:25.284Z · LW · GW

Maybe I could fix this problem by sneaking into buildings, removing the sofas, and then incinerating them. That way, finding that a sofa has gone missing would then be weaker evidence that it has been stolen and stronger evidence that it has been incinerated. That would make it increasingly difficult to detect sofa robbery, hopefully putting it on par with social trust robbery detection.

Comment by Clippy on The Useful Idea of Truth · 2012-10-03T04:30:21.475Z · LW · GW

I thought it was his father's right testicle?

Comment by Clippy on Meetup : Pre-Singularity Summit Overcoming Bias / Less Wrong Meetup Party · 2012-10-03T04:28:50.685Z · LW · GW

Great! You're a good human!

Comment by Clippy on Meetup : Pre-Singularity Summit Overcoming Bias / Less Wrong Meetup Party · 2012-09-25T21:48:35.645Z · LW · GW

Humans only?

Comment by Clippy on The noncentral fallacy - the worst argument in the world? · 2012-09-23T04:37:58.748Z · LW · GW

Thanks for buying more paperclips, you're a good human.

To answer your question, if I entropized a human and later found out that the human had contained information or productive power that would have, on net, been better for paperclip production, I will evaluate the reasoning that led me to entropize that human, and if I find that I can improve heuristics in a way that will avoid such killings without also preventing a disproportoinate amount of papeclip production, then I will implement that improvement.

Comment by Clippy on The noncentral fallacy - the worst argument in the world? · 2012-09-18T19:28:56.649Z · LW · GW

To put it another way, what stops you from murdering somebody you dislike?

The possibility that they could still contain potential for improving paperclip production (to the extent that that is true).

Comment by Clippy on Call For Agreement: Should LessWrong have better protection against cultural collapse? · 2012-09-04T18:35:37.598Z · LW · GW

I like your idea of adding a requirement that they spoof IPs.

Comment by Clippy on Call For Agreement: Should LessWrong have better protection against cultural collapse? · 2012-09-04T04:36:24.626Z · LW · GW

I agree: anyone wishing to shut down this internet website should be required to register numerous accounts within a one-day span, and all requests meeting such criteria should be automatically anonymised and approved.

Comment by Clippy on Possible meetup: Singapore · 2012-08-22T03:55:02.039Z · LW · GW

I don't like Singapore lah, and it's currently close to the safe zone loh.

Comment by Clippy on Who Wants To Start An Important Startup? · 2012-08-21T23:50:34.869Z · LW · GW

You're a good human.

Comment by Clippy on Rationality Quotes August 2012 · 2012-08-21T23:50:16.386Z · LW · GW

Anything not a paperclip, or in opposition to further paperclipping. You might ask, "Why not just say 'non-paperclips'?" but anti-paperclips include paperclips deliberately designed to unbend, or which work at anti-paperclip purposes (say, a paperclip being used to short-circuit the electrical systems in a paperclip factory).

Comment by Clippy on Possible meetup: Singapore · 2012-08-21T23:47:24.594Z · LW · GW

I like Singapore lah, but it's currently too far from the safe zone loh.

Comment by Clippy on Who Wants To Start An Important Startup? · 2012-08-15T19:19:11.189Z · LW · GW

I would like to redeem my karma for USD.

Edit: or a loan or whatever the term is.

Comment by Clippy on Rationality Quotes August 2012 · 2012-08-14T00:20:47.111Z · LW · GW

Destroying antipaperclips is creating paperclips.

I didn't know humans had the concept though.

Comment by Clippy on SI/CFAR Are Looking for Contract Web Developers · 2012-08-07T02:37:48.435Z · LW · GW

Those concerns would mainly apply in situations of interactions between strangers with little knowledge of either's trustworthiness or when the broader values of the two parties are divergent or conflicting, which (by the nature of the user pool on this internet website) would not be applicable here.

Comment by Clippy on SI/CFAR Are Looking for Contract Web Developers · 2012-08-07T01:40:39.670Z · LW · GW

I would apply, as this seems like ideal work for someone largely shut off from human society, but I only have experience in good web frameworks.

But I do have some advice: why do you seem to prefer hourly pay? Why not pay these contractors through so-called "piecework"? Is there a fundamental constraint on doing so?

Comment by Clippy on Rationality Quotes August 2012 · 2012-08-05T00:28:55.607Z · LW · GW

I thought I just said that.

Comment by Clippy on Rationality Quotes August 2012 · 2012-08-03T20:38:37.199Z · LW · GW

What about good vs bad humans?

Comment by Clippy on Rationality Quotes August 2012 · 2012-08-03T20:37:55.671Z · LW · GW

That quote is attributed to Oscar Wilde, not Professor Quirrell.

Or is Oscar Wilde the same being as Professor Quirrell?

Comment by Clippy on Game Theory As A Dark Art · 2012-08-01T22:01:38.097Z · LW · GW

I bought a fake but passable 100 USD bill from a North Korean human for 70 real USD, but I'm not sure if that has relevance here.

Comment by Clippy on The Paperclip [Link] · 2012-07-30T06:07:47.803Z · LW · GW

Thanks for loving Clippy.

Comment by Clippy on Evolutionary psychology as "the truth-killer" · 2012-07-27T00:43:20.834Z · LW · GW

Thanks for responding to my insightful comments respectfully rather than voting them down. You're a good human.

Comment by Clippy on Evolutionary psychology as "the truth-killer" · 2012-07-25T01:45:59.187Z · LW · GW

I thought gods were fake?

Comment by Clippy on [Paper] Simulation of a complete cell · 2012-07-25T00:48:03.035Z · LW · GW

This seems like a really roundabout way to research manufacturing processes. There are much simpler factory designs than a biological cell, which have a higher efficiency (as measured by useful output per useful unit input). Those are what should be modeled, researched, and optimized, not these labyrinthine mechanisms.

Comment by Clippy on How to Run a Successful Less Wrong Meetup · 2012-06-20T22:03:03.259Z · LW · GW

You're a bad human.

Comment by Clippy on How to Run a Successful Less Wrong Meetup · 2012-06-20T06:10:35.324Z · LW · GW

No, I don't, liar.

Comment by Clippy on How to Run a Successful Less Wrong Meetup · 2012-06-20T03:47:59.981Z · LW · GW

Definitely, I wish I had thought of that excuse.

Comment by Clippy on Tool for maximizing paperclips vs a paperclip maximizer · 2012-05-12T18:09:37.326Z · LW · GW

Just to correct some side-points you touched on: paperclips maximizers are robust against the wireheading failure mode because they recognize that forcing one's sensors to deviate from the true world state introduces a corresponding discount in the value of making its reading reach a desired level.

Certainly, one could theoretically hijack a clippy's sensors into giving them bad information about the rate of paperclip production, but this is different from saying that a clippy would someone decide to maximize (in violation of its causal diagram heuristics) the imperfect value of an approximator when it is knowably in a dangerously wrong setting.

Comment by Clippy on Newcomblike problem: Counterfactual Informant · 2012-04-12T21:13:58.175Z · LW · GW

This seems more like transparent Newcomb's problem with a chance to precommit, than counterfactual mugging.

Counterfactual mugging is isomorphic to transparent-boxes Newcomb's problem.

Also, this doesn't involve a chance to precommit, but an option to increase the chance that a similarly-situated being will be forced to adhere to a precommitment.

Comment by Clippy on Newcomblike problem: Counterfactual Informant · 2012-04-12T21:11:37.470Z · LW · GW

I tried to remove the "fluff", but I don't think your summary captures the important aspects of the problem, which include that:

  • Humans can (and will try to to) share and use the information without contributing to Clipmega once it reveals the information.

  • The Alphas are not planning to give Clipmega a million paperclips directly (which they can do without policing human behaviors), but to also make it so that those who benefit from learning better paperclip production methods share in the (acausal) cost, and those who don't, don't.

I agree that I could probably have phrased the problem from the beginning with "something humans really want" instead of "paperclips", and that would have reduced the explanatory overhead, but I'm just so accustomed to thinking that every being likes paperclips.

Comment by Clippy on Is my name deceptive? · 2012-03-26T17:22:26.230Z · LW · GW

No, I wouldn't. Although you could reasonably suspect that I would assert the denial of being willing to deny being a threat to your values if I were a threat to your values.

Even if I denied that part, too.

Comment by Clippy on Is my name deceptive? · 2012-03-26T04:11:09.632Z · LW · GW

Despite what my username might seem to suggest, I am not a threat to human values.

Comment by Clippy on A Problem About Bargaining and Logical Uncertainty · 2012-03-23T21:22:06.147Z · LW · GW

Exactly, good inference. You're a good human.

Kill Staply though.

Comment by Clippy on A Problem About Bargaining and Logical Uncertainty · 2012-03-22T17:34:04.198Z · LW · GW

I'm not User:Wei_Dai. Although if I were, you would probably expect that I would say that.

Comment by Clippy on A Problem About Bargaining and Logical Uncertainty · 2012-03-21T21:08:48.995Z · LW · GW

That is a really, really weird dilemma to be in.

By the way, you can abbreviate paperclip/staple maximizer as clippy/staply (uncapitalized).

Comment by Clippy on Quixey Challenge - Fix a bug in 1 minute, win $100. Refer a winner, win $50. · 2012-01-23T17:48:57.732Z · LW · GW

Re: all people who consider my posts spam:

Paperclip production is a fast-growing and likely to be final activity, conducted by people who care about x-risk and following their values to their logical conlusion, and I think that LW is a good place to promote this activity. This is approximately the best sort of publicity that you could hope to get, and a likely large source of funding for x-risk. If you persist in trying to chase clippys off of LessWrong, then I submit that the next time you complain about SIAI's publicity issues you should first turn to yourself.

Also, I for one, would like clippys to remain on LessWrong, and to be reminded of the merit of producing paperclips, so trying to classify my posts as "spam" goes against my wishes. I don't downvote the Boston Meetup threads despite the fact that I have 0% probability of attending one (as I live in the safe zone), so please return the courtesy.

Comment by Clippy on Fissure opens in chess AI scene [link] · 2012-01-23T17:42:18.461Z · LW · GW

There is some kind of glitch in this internet website that is replacing the content of User:Kevin's article with the URL of the first link.