timtyler

• timtylerDec 14, 2013, 10:46 PM

  1 point

  in reply to: Nornagest’s comment on: Walk­through of the Tiling Agents for Self-Mod­ify­ing AI paper

  The question’s more about what function’s generating the fitness landscape you’re looking at (using “fitness” now in the sense of “fitness function”). “Survival” isn’t a bad way to characterize that fitness function—more than adequate for eighth-grade science, for example. But it’s a short-tern and highly specialized kind of survival [...]

  Evolution is only as short-sighted as the creatures that compose its populations. If organisms can do better by predicting the future (and sometimes they can) then the whole process is a foresightful one. Evolution is often characterised as ‘blind to the future’ - but that’s just a mistake.

• timtylerDec 14, 2013, 9:07 PM

  0 points

  in reply to: Nornagest’s comment on: Walk­through of the Tiling Agents for Self-Mod­ify­ing AI paper

  Even to the extent that natural selection can be said to be care about anything, saying that survival is that thing is kind of misleading.

  Well, I have gone into more details elsewhere.

  It’s perfectly normal for populations to hill-climb themselves into a local optimum and then get wiped out when it’s invalidated by changing environmental conditions that a more basal but less specialized species would have been able to handle, for example.

  Sure. Optimization involves going uphill—but you might be climbing a mountain that is sinking into the sea. However, that doesn’t mean that you weren’t really optimizing—or that you were optimizing something other than altitude.

• timtylerDec 14, 2013, 8:25 PM

  −10 points

  in reply to: ialdabaoth’s comment on: Walk­through of the Tiling Agents for Self-Mod­ify­ing AI paper

  Nature only “cares” about survival. However, that’s also exactly what we should care about—assuming that our main priority is avoiding eternal obliteration.

• timtylerDec 14, 2013, 7:42 PM

  −7 points

  in reply to: ialdabaoth’s comment on: Walk­through of the Tiling Agents for Self-Mod­ify­ing AI paper

  In biology, the “how can you trust your descendants?” question is rarely much of an issue—typically, you can’t.

  The issue of how to ensure your descendants don’t get overrun by parasites is more of a real problem.

  Nature’s most common solution involves sexual reproduction—and not “tiling”. It’s not necessarily a good thing to rule out the most common solution in the statement of a problem.

• timtylerDec 14, 2013, 4:34 PM

  −6 points

  on: Walk­through of the Tiling Agents for Self-Mod­ify­ing AI paper

  We want to be able to consider agents which build slightly better versions of themselves, which build slightly better versions of themselves, and so on. This is referred to as an agent “tiling” itself. This introduces a question: how can the parent agent trust its descendants?

  It also raises other questions—such as: how will such a monoculture resist exploitation by parasites?

• timtylerDec 14, 2013, 4:18 PM

  2 points

  in reply to: byrnema’s comment on: LINK: AI Re­searcher Yann LeCun on AI function

  Here is one of my efforts to explain the links: Machine Forecasting.

• timtylerDec 14, 2013, 4:16 PM

  0 points

  in reply to: ShardPhoenix’s comment on: LINK: AI Re­searcher Yann LeCun on AI function

  I’m pretty sure that we suck at prediction—compared to evaluation and tree-pruining. Prediction is where our machines need to improve the most.

• timtylerDec 14, 2013, 3:01 AM

  0 points

  in reply to: Eliezer Yudkowsky’s comment on: LINK: AI Re­searcher Yann LeCun on AI function

  search is not the same problem as prediction

  It is when what you are predicting is the results of a search. Prediction covers searching.

• timtylerDec 14, 2013, 2:50 AM

  0 points

  on: LINK: AI Re­searcher Yann LeCun on AI function

  It is interesting that his view of AI is apparently that of a prediction tool [...] rather than of a world optimizer.

  If you can predict well enough, you can pass the Turing test—with a little training data.

• timtylerDec 10, 2013, 11:56 AM

  −2 points

  in reply to: Brian_Tomasik’s comment on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  If we’re talking reference classes, I would cite the example that the first hominid species to develop human-level intelligence took over the world.

  Note that humans haven’t “taken over the world” in many senses of the phrase. We are massively outnumbered and out-massed by our own symbionts—and by other creatures.

  Machine intelligence probably won’t be a “secret” technology for long—due to the economic pressure to embed it.

  While its true that things will go faster in the future, that applies about equally to all players—in a phenomenon commonly known as “internet time”.

• timtylerDec 10, 2013, 2:30 AM

  −6 points

  in reply to: nshepperd’s comment on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  Standard? Invoking reference classes is a form of arguing by analogy. It’s a basic thinking tool. Don’t knock it if you don’t know how to use it.

• timtylerDec 10, 2013, 12:11 AM

  0 points

  in reply to: nshepperd’s comment on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  Doesn’t someone have to hit the ball back for it to be “tennis”? If anyone does so, we can then compare reference classes—and see who has the better set. Are you suggesting this sort of thing is not productive? On what grounds?

• timtylerDec 9, 2013, 11:15 AM

  −4 points

  in reply to: passive_fist’s comment on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  As has been pointed out numerious times on lesswrong, history is not a very good guide for dealing with AI since it is likely to be a singular (if you’ll excuse the pun) event in history. Perhaps the only other thing it can be compared with is life itself [...]

  What, a new thinking technology? You can’t be serious.

• timtylerDec 9, 2013, 2:21 AM

  −5 points

  in reply to: Brian_Tomasik’s comment on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  The first OS didn’t take over the world. The first search engine didn’t take over the world. The first government didn’t take over the world. The first agent of some type taking over the world is dramatic—but there’s no good reason to think that it will happen. History better supports models where pioneers typically get their lunch eaten by bigger fish coming up from behind them.

• timtylerDec 8, 2013, 8:10 PM

  −1 points

  on: In­ter­na­tional co­op­er­a­tion vs. AI arms race

  whoever builds the first AI can take over the world, which makes building AI the ultimate arms race.

  As the Wikipedians often say, “citation needed”. The first “AI” was built decades ago. It evidently failed to “take over the world”. Possibly someday a machine will take over the world—but it may not be the first one built.

• timtylerDec 8, 2013, 12:04 AM

  −2 points

  on: Ques­tions and com­ments about Eliezer’s Dec. 2 2013 Oxford speech

  I didn’t buy the alleged advantage of a noise free environment. We’ve known since von-Neumann’s paper titled:

  PROBABILISTIC LOGICS AND THE SYNTHESIS OF RELIABLE ORGANISMS FROM UNRELIABLE COMPONENTS

  ...that you can use unreliable computing components to perform reliable computation—with whatever level of precision and reliability that you like.

  Plus the costs of attaining global synchrony and determinism are large and massively limit the performance of modern CPU cores. Parallel systems are the only way to attain large computing capacities—and you can’t guarantee every component in a large parallel system will behave deterministically. So: most of the future is likely to lie with asynchronous systems and hardware indeterminism, rather contrary to Yudkowsky’s claims.

• timtylerNov 29, 2013, 1:20 PM

  7 points

  in reply to: passive_fist’s comment on: A model of AI development

  The point I was trying to make was more along the lines that choosing which parameters to model allows you to control the outcome you get. Those who want to recruit people to causes associated with preventing the coming robot apocalypse can selectively include competitive factors, and ignore factors leading to cooperation—in order to obtain their desired outcome.

  Today, machines are instrumental in killing lots of people, but many of them also have features like air bags and bumpers, which show that the manufacturers and their customers are interested in safety features—and not just retail costs. Skipping safety features has disadvantages—as well as advantages—to the manufacturers involved.

• timtylerNov 29, 2013, 12:50 AM

  1 point

  on: A model of AI development

  People have predicted that corporations will be amoral, ruthless psychopaths too. This is what you get when you leave things like reputations out of your models.

  Skimping on safety features can save you money. However, a reputation for privacy breaches, security problems and accidents doesn’t do you much good. Why model the first effect while ignoring the second one? Oh yes: the axe that needs grinding.

• timtylerNov 26, 2013, 11:03 AM

  −2 points

  in reply to: Daniel_Burfoot’s comment on: Gel­man Against Parsimony

  Bayesian methods certainly require relative parsimony, in the sense that the model complexity needs to be small compared to the quantity of information being modeled.

  Not really. Bayesian methods can model random noise. Then the model is of the same size as the data being modeled.

• timtylerNov 26, 2013, 10:51 AM

  0 points

  on: Gel­man Against Parsimony

  I often use simple models–because they are less effort to fit and, especially, to understand. But I don’t kid myself that they’re better than more complicated efforts!

  Recommended reading: Boyd and Richerson’s Simple Models of Complex Phenomena.