All of roll's Comments + Replies

roll00

SI is openly concerned with exactly that type of optimization, and how it becomes unsafe

Any references? I haven't seen anything that is in any way relevant to the type of optimization that we currently know how to implement. The SI is concerned with notion of some 'utility function', which appears very fuzzy and incoherent - what it is, a mathematical function? What does it have at input and what it has at output? The number of paperclips in the universe is given as example of 'utility function', but you can't have 'universe' as the input domain to a ma... (read more)

roll00

That depends what your initial probability is and why. If it already low due to updates on predictions about the system, then updating on "unpredictable" will increase the probability by lowering the strength of those predictions. Since destruction of humanity is rather important, even if the existential AI risk scenario is of low probability it matters exactly how low.

The importance should not weight upon our estimation, unless you proclaim that I should succumb to a bias. Furthermore, it is the destruction of the mankind that is the predicti... (read more)

roll-10

Well, that's the Luke's aspirations; I was referring to the work done so far. The whole enterprise has the feeling of over optimistic startup with ill defined extremely ambitious goals; those don't have any success rate even for much much simpler goals.

roll20

A suggestion: it may be a bad idea to use word 'artificial intelligence' in the name without qualifiers, as to serious people in the field

  • the 'artificial intelligence' has much, much broader meaning than what SI is concerning itself with

  • there is very significant disdain for the commonplace/'science fiction' use of 'artificial intelligence'

roll00

Center for Helpful Artificial Optimizer Safety

What concerns me is lack of research into artificial optimizers in general... Artificial optimizers are commonplace already, they are algorithms to find optimal solutions to mathematical models, not to optimize the real world in the manner that SI is concerned with (correct me if I am wrong). Furthermore the premise is that such optimizers would 'foom', and i fail to see how foom is not a type of singularity.

0[anonymous]
Recent published SI work concerns AI safety. They have not recently published results on AGI, to whatever extent that is separable from safety research, for which I am very grateful. Common optimization algorithms do apply to mathematical models, but that doesn't limit their real world use; an implemented optimization algorithm designed to work with a given model can do nifty things if that model roughly captures the structure of a problem domain. Or to put it simply, models model things. SI is openly concerned with exactly that type of optimization, and how it becomes unsafe if enough zealous undergrads with good intentions throw this, that, and their grandmother's hippocampus into a pot until it supposedly does fantastic venture capital attracting things. The fact that SI is not writing papers on efficient adaptive particle swarms is good and normal for an organization with their mission statement. Foom was a metaphorical onomatopoeia for an intelligence explosion, which is indeed a commonly used sense of the term "technological singularity".
roll00

Hmm what do you think would have happened with that someone if the name was more attractive and that person spent more time looking into SI? Do you think that person wouldn't ultimately dismiss it? Many of the premises here seem more far fetched than singularity. I know that from our perspective it'd be great to have feedback from such people, but it wastes their time and it is unclear if that is globally beneficial.

roll30

From what I gathered SI's relevance rests upon an enormous conjunction of implied and a very narrow approach as solution, both of which were decided upon significant time in the past. Subsequently, truly microscopic probability of relevance is easily attained; I estimate at most 10^-20 due to multiple use of narrow guesses into a huge space of possibilities.

4John_Maxwell
Hm, most of the immediate strategies SI is considering going forward strike me as fairly general: http://lesswrong.com/r/discussion/lw/cs6/how_to_purchase_ai_risk_reduction/ They're also putting up these strategies for public scrutiny, suggesting they're open to changing their plans. If you're referring to sponsoring an internal FAI team, Luke wrote: BTW, I wish to reinforce you for the behavior of sharing a dissenting view (rationale: view sharing should be agnostic to dissent/assent profile, but sharing a dissenting view intuitively risks negative social consequences, an effect that would be nice to neutralize), so I voted you up.
roll00

I certainly agree, and I am not even sure what the official SI position is on the probability of such failure. I know that Eliezer in hist writing does give the impression that any mistake will mean certain doom, which I believe to be an exaggeration. But failure of this kind is fundamentally unpredictable, and if a low probability even kills you, you are still dead, and I think that it is high enough that the Friendly AI type effort would not be wasted.

Unpredictable is a subjective quality. It'd look much better if the people speaking of unpredictabili... (read more)

0Armarren
That depends what your initial probability is and why. If it already low due to updates on predictions about the system, then updating on "unpredictable" will increase the probability by lowering the strength of those predictions. Since destruction of humanity is rather important, even if the existential AI risk scenario is of low probability it matters exactly how low. This of course has the same shape as Pascal's mugging, but I do not believe that SI claims are of low enough probability to be dismissed as effectively zero. That was in fact my point, which might indicate that we are likely to be talking past each other. What I tried to say is that an artificial intelligence system is not necessarily constructed as an explicit optimization process over an explicit model. If the model and the process are implicit in its cognitive architecture then making predictions about what the system will do in terms of a search are of limited usefulness. And even talking about models, getting back to this: On further thought, this is not even necessarily true. The solution space and the model will have to be pre-cut by someone (presumably human engineers) who doesn't know where the solution actually is. A self-improving system will have to expand both if the solution is outside them in order to find it. A system that can reach a solution even when initially over-constrained is more useful than the one that can't, and so someone will build it. I do not understand what you are saying here. If you mean that by unstable I mean a highly specific trajectory a system that lost stability will follow, then it is because all those trajectories where the system crashes and burns are unimportant. If you have a trillion optimization systems on a planet running at the same time you have to be really sure that nothing can't go wrong. I just realized I derailed the discussion. The whole AGI in specialized AI world is irrelevant to what started this thread. In the sense of chronology of be
roll00

There's probably a lot of low hanging fruit, for example use of correct priors, e.g. given Gaussian prior distribution, a quite strong proof should be needed before you should believe someone (including yourself) has very high intelligence or expertise on a task.

Furthermore, many ways of evaluating people are to some extent self reinforcing as the people being evaluated are aware of evaluation. A smart person or expert can relatively cheaply demonstrate intelligence and/or expertise, in some way that provides very strong evidence, and will do so even for ... (read more)

roll00

I think what may be confusing about expected outcome is the name. You don't actually expect to get 5 dollars out of this :) . You don't even expect to get, say, 5 million dollars after 1 million games, such would be rather unlikely. You do expect to get 5$ per game if you played infinitely many games, though, and if you are playing such games on small amounts of money you can choose the game to play based on expected outcome.

roll-20

Just because it doesn't do exactly what you want doesn't mean it is going to fail in some utterly spectacular way.

You aren't searching for solutions to a real world problem, you are searching for solutions to a model (ultimately, for solutions to systems of equations), and not only you have limited solution space, you don't model anything irrelevant. Furthermore, the search space is not 2d and not 3d, and not even 100d, the volume increases really rapidly with size. The predictions of many systems are fundamentally limited by Lyapunov's exponent. I suggest... (read more)

0Armarren
I certainly agree, and I am not even sure what the official SI position is on the probability of such failure. I know that Eliezer in hist writing does give the impression that any mistake will mean certain doom, which I believe to be an exaggeration. But failure of this kind is fundamentally unpredictable, and if a low probability even kills you, you are still dead, and I think that it is high enough that the Friendly AI type effort would not be wasted. That is true in the trivial sense that everything can be described as equations, but when thinking how computation process actually happens this becomes almost meaningless. If the system is not constructed as a search problem over high dimensional spaces, then in particular its failure modes cannot be usefully thought about in such terms, even if it is fundamentally isomorphic to such a search. Or it will be created by intuitively assembling random components and seeing what happens. In which case there is no guarantee what it will actually do to its own model or even to what it is actually solving for. Convincing AI researches to only allow an AI to self modify when it is stable under self modification is a significant part of the Friendly AI effort. There are very few statements that are true about "everyone" and I am very confident that this is not one of them. Even if most people with actual means to build one want specialized and/or tool AIs, you only need one unfriendly-successful AGI project to potentially cause a lot of damage. This is especially true as both hardware costs fall and more AI knowledge is developed and published, lowering the entry costs. To be dangerous AGI doesn't have to overtake specialized intelligences, it has to overtake humans. Existence of specialized AIs is either irrelevant or increases the risks from AGI, since they would be available to both, and presumably AGIs would have lower interfacing costs.
roll-10

Well, if that's the whole point, SI should dissolve today (shouldn't even have formed in first place). The software is not magic; "once the software can achieve any serious objectives" is when we know how to restrict the search space; it won't happen via mere hardware improvement. We don't start with philosophical ideal psychopathic 'mind', infinitely smart, and carve friendly mind out of it. We build our sculpture grain by grain using glue.

3Armarren
Just because software is built line by line doesn't mean it automatically does exactly what you want. In addition to outright bugs any complex system will have unpredictable behaviour, especially when exposed to real word data. Just because the system can restrict the search space sufficiently to achieve an objective doesn't mean it will restrict itself only to the parts of the solution space the programmer wants. The basic purpose of Friendly AI project is to formalize human value system sufficiently that it can be included into the specification of such restriction. The argument made by SI is that there is a significant risk a self-improving AI can increase in power so rapidly, that unless such restriction is included from the outset it might destroy humanity.
roll40

I think the bigger issue is the collapsing of the notion of 'incredibly useful software that would be able to self improve and solve engineering problems' with philosophical notion of mind. The philosophical problem of how do we make the artificial mind not think about killing mankind, may not be solvable over the philosophical notion of the mind, and the solutions may be useless. However, practically it is a trivial part of much bigger problem of 'how do we make the software not explore the useless parts of the solution space'; it's not the killing of man... (read more)

5Armarren
Well, obviously, since it is pretty much the problem we have now. The whole point of the Friendly AI as formulated by SI is that you have to solve the former problem before the latter is solved, because once the software can achieve any serious objectives it will likely cause enormous damage on its way there.
roll00

What does Solomonoff Induction actually say?

I believe this one has been closed ages ago by Alan Turing, and practically demonstrated for approximations by the investigation into busy beaver function for example. We won't be able to know BB(10) from God almighty. Ever.

0koning_robot
I'm not sure what you're trying to say here, but if you consider this a relative weakness of Solomonoff Induction, then I think you're looking at it the wrong way. We will know it as well as we possibly could given the evidence available. Humans are subject to the constraints that Solomonoff Induction is subject to, and more.
roll00

Of course, but one can lack information and conclude "okay, I don't have enough information", or one may not arrive at such conclusion due to the overconfidence (for example).

roll00

That's an interesting question. Eliezer has said on multiple occasions that most AI researchers now are lunatics, and he is probably correct; how would outsider distinguish Friendly AI team from the most? The fact of concern with safety, alone, is a poor indicator of sanity; many insane people are obsessed with safety of foods, medications, air travel, safety from the government, etc etc.

roll00

Well, the value of life, lacking specifiers, should be able to refer to the total of the value of life (as derived from other goals and intrinsic value if any); my post is rather explicit in that it speaks of the total. Of course you can take 'value life' to mean only the intrinsic value of life, but it is pretty clear that is not what OP meant if we assume that OP is not entirely stupid. He is correct in the sense that the full value of life is affected by rationality. Rational person should only commit suicide in some very few circumstances where it trul... (read more)

roll00

This raises interesting off-topic question: does 'intelligence' itself confer significant advantage over such methods (which can certainly be implemented without anything resembling agent's real world utility)?

We are transitioning to being bottlenecked (in our technological progress, at least) by optimization software implementing such methods, rather than being bottlenecked by our intelligence (that is in part how the exponential growth is sustained despite constant human intelligence); if the AI can't do a whole lot better than our brainstorming, it probably won't have upper hand over dedicated optimization software.

roll00

I think something is missing here. Suppose that water has some unknown property Y that may allow us to do Z. This very statement requires that water somehow refers to object in the real world, so that we would be interested in experimenting with the water in the real world instead of doing some introspection into our internal notion of 'water'. We want our internal model of water to match something that is only fully defined externally.

Other example, if water is the only liquid we know, we may have combined notions of 'liquid' and 'water', but as we explo... (read more)

roll-20

Does a purely rational mind value life less or more?

Specifying that a mind is rational does not specify how much it values life.

That is correct but it is also probably the case that rational mind would propagate better from it's other values, to the value of it's own life. For instance if your arm is trapped under boulder, human as is would either be unable to cut off own arm, or do it at suboptimal time (too late), compared to the agent that can propagate everything that it values in the world, to the value of it's life, and have that huge value win... (read more)

0DanielLC
You were talking about instrumental values? I thought you were talking about terminal values.
roll-20

Well, one has to distinguish between purely rational being that has full set of possible propositions with correct probabilities assigned to them, and a bounded agent which has a partial set of possible propositions, generated gradually by exploring starting from some of the most probable propositions; the latter can't even do Bayesian statistics properly due to the complex non-linear feedback via proposition generation process, and is not omniscient enough to foresee as well as your argument requires.