All of Armarren's Comments + Replies

Let's try a car analogy for a compatibilist position, as I understand it: there is car, and why does it move? Because it has an engine and wheels and other parts all arranged in a specific pattern. There is no separate "carness" that makes it move ("automobileness" if you will), it is the totality of its parts that makes it a car.

Will is the same, it is the totality of your identity which creates a process by which choices are made. This doesn't mean there is no such thing any more than the fact that a car is composed of identifiable parts means that no car exists, it is just not a basic indivisible thing.

There are no discrete "worlds" and "branches" in quantum physics as such. Once two regions in state space are sufficiently separated to no longer significantly influence each other they might be considered split, which makes the answer to your question "yes" by definition.

0RogerS
This seems to conflict with references to "many worlds" and "branch points" in other comments, or is the key word "discrete"? In other words, the states are a continuum with markedly varying density so that if you zoom out there is the appearance of branches? I could understand that expect for cases like Schroedinger's cat where there seems to be a pretty clear branch (at the point where the box is opened, i.e. from the point of view of a particular state if that is the right terminology). From the big bang there are an unimaginably large number of regions in state space each having an unimaginably small influence. It's not obvious, but I can perfectly well believe that the net effect is dominated by the smallness of influence, so I'll take your word for it.

The highly specific predictions should be lowered in their probability when updating on the statement like 'unpredictable'.

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,... (read more)

0roll
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 prediction being made here. Via multitude of assumptions, the most dubious one being that the system will have real-world, physical goal. Number of paperclips is not easy. Sorry, you are factually wrong as of how the design of automatic tools work. Rest of your argument presses too hard to recruit multitude of importance related biases and cognitive fallacies that were described on this very site. No I don't, if the systems that work right took all the low hanging fruit from picking by one that goes wrong. You seem to keep forgetting of all the software that is fundamentally different from human mind, but solves the problems very well. The issue reads like a belief in extreme superiority of man over machine, except it is a superiority of anthropomorphized software over all other software.

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

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 n... (read more)

0roll
Unpredictable is a subjective quality. It'd look much better if the people speaking of unpredictability had demonstrable accomplishment. If there is a trillion equally probable unpredictable outcomes, out of which only a small integer is destruction of mankind, even though it is still technically fundamentally unpredictable the probability is low. Unpredictability does not imply likehood of the scenario; if anything, unpredictability implies lower risk. I am sensing either a bias or dark arts; the unpredictable is a negative word. The highly specific predictions should be lowered in their probability when updating on the statement like 'unpredictable'. Not everything is equally easy to describe as equations. For example we don't know how to describe number of real world paperclips with a mathematical equation. We can describe performance of a design with equation, and then solve for maximum, but that is not identical to 'maximizing performance of real world chip'. The problem is that of finding a point in a high dimensional space. I think you have a very narrow vision of 'unstable'. To be dangerous AGI has to win in the future ecosystem where the fruit been taken. The general is a positive sounding word, beware of halo effect. I believe that is substantially incorrect. Suppose that there was an AGI in your basement, connected to internet, in the ecosystem of very powerful specialized AIs. The internet is secured by specialized network security AI and would have been taken by specialized botnet if it was not; you don't have a chip fabrication plant in your basement; the specialized AIs elsewhere are running on massive hardware designing better computing substrates, better methods of solving, and so on. What exactly this AGI is going to do? This is going nowhere. Too much anthropomorphization.

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 ... (read more)

-2roll
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 you stop thinking in terms of concepts like 'improve'. If something self improves at software level, that'll be a piece of software created with very well defined model of changes to itself, and the very self improvement will be concerned with cutting down the solution space and cutting down the model. If something self improves at hardware level, likewise for the model of physics. Everyone wants artificial rainman. The autism is what you get from all sorts of random variations to baseline human brain; looks like the general intelligence that expands it's model and doesn't just focus intensely is a tiny spot in the design space. I don't see why expect general intelligence to suddenly overtake specialized intelligences; the specialized intelligences have better people working on them, have the funding, and the specialization massively improves efficiency; superhuman specialized intelligences require lower hardware power.
-2private_messaging
That sounds way less scary when you consider actual software that is approaching recursive self improvement and get more specific than vague "increase in power". It's just generic ignorant anti-technology talk that relies on vague concepts like "power" and dissipates once you get in any way specific. The software also tends not to do what you want it to do for sake of this argument. There's an enormous gap between 'not doing exactly what we want' and doing exactly what you want for this argument to work. The automated engineering software simulates microscopic material interaction; vague self improvement and increases in power only make it better at not doing unrelated stuff.

Long before you have to worry about the software finding an unintended way to achieve the objective, you encounter the problem of software not finding any way to achieve the objective

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.

-1roll
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.

As often happens, it is to quite an extent a matter of definitions. If by an "end" you mean a terminal value, then no purely internal process can change that value, because otherwise it wouldn't be terminal. This is essentially the same as the choice of reasoning priors, in that anything that can be chosen is, by definition, not a prior, but a posterior of the choice process.

Obviously, if you split the reasoning process into sections, then posteriors of a certain sections can become priors of the sections following. Likewise, certain means can be... (read more)

2Vladimir_Nesov
A notion of "terminal value" should allow possibility of error in following it, including particularly bad errors that cause value drift (change which terminal values an agent follows).
0RomeoStevens
Some of your terminal values can modify other terminal values though. Rational investigation can inform you about optimal trade-offs between them. Edit: Tradeoffs don't change that you want more of both A and B. Retracted.