TAG

Karma: 753

TAG 27 Sep 2022 15:55 UTC
1 point
0 ∶ 0
in reply to: Jon Garcia’s comment on: ACHIEVABLE AGI?

There is no evidence that the structure and function of the human brain (along with its physical embodiment) is insufficient to explain all aspects of human intelligence and consciousness.

https://en.wikipedia.org/wiki/Hard_problem_of_consciousness

TAG 26 Sep 2022 12:18 UTC
3 points
1 ∶ 0
on: There’s One Thing Futurists are Never Wrong About

Substance dualists generally insist upon the “stillbirth” or p-zombie possibilities

You don’t have to be a substance dualist to believe a sim could be a zombie: there’s an argument based on physicalism.

Computation isn’t causation. Computation is essentially a lossy, high level description of the physical behaviour. It’s possible for qualia to depend on some aspects of the physics that isn’t captured the computational description …which means that out of two systems running the same algorithm on different hardware,one could have qualia , but the other not. The other is a kind of zombie, but not a p-zombie because of the physical difference. Moreover, it’s possible,given physicalism , for qualia to depend on the real physics ,not on comoutattii a at that level of granularity.

TAG 26 Sep 2022 12:05 UTC
1 point
1 ∶ 0
in reply to: MondSemmel’s comment on: UI/UX From the Dark Ages

The underlying concepts and technologies influenced both the Apple Macintosh and Microsoft Windows graphical user interface operating systems in the 1980s and 1990s.

As far as ordinary users are concerned, graphical UI is from the late eighties or early nineties, when it could be implemented affordably. It was arguably ahead of its time in the seventies and sixties.

TAG 24 Sep 2022 16:16 UTC
1 point
0 ∶ 0
on: “Free Will” in a Computational Universe

In dualist implementations of libertarian free will, a mind can choose any of a given set of actions. There is no knowledge as to what choice the mind will make ahead of time. Before the mind makes its choice, its choice is undetermined.

Isomorphically, an algorithm can choose any of a given set of actions. There is no knowledge as to what choice the algorithm will make ahead of time. Before the algorithm (or an extensional equivalence thereof) is computed, its choice is undetermined

No , it’s just unknown. The algorithm could be computer by a predictor, and if it always produces the same output, then it’s deterministic. Determinism is the possibility of prediction. If one particular agent can’t make a prediction in practice, that doesn’t mean determinism has vanished.

TAG 24 Sep 2022 13:25 UTC
1 point
0 ∶ 0
in reply to: tailcalled’s comment on: Why are we sure that AI will “want” something?
There’s the Gwern-style argument that successive generations AIs will get more agentive as a side of effect of the market demanding more powerful AIs. There’s a counterargument that non-one wants power that they can’t control, so that AIs will never be more than force multipliers .. although that’s still fairly problematic.

TAG 24 Sep 2022 13:12 UTC
1 point
0 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

What are you expecting to be able to do here?

Show that coherence is simple but inadequate, and decoherence is adequate but not simple .

Shrodingers cat. Cat is in a superposition of alive and dead. Scientist opens box. Scientist is in superposition of feeding live cat and burying dead cat.

The two problems with this account are 1) “alive” and “dead” are classical states—a classical basis is assumed. and 2) the two states of the observer are assumed to be non-interacting and unaware of each other. But quantum mechanics itself gives no reason to suppose that will be the case. In both cases, it needs to be shown, and not just assumed that normality—perceptions “as if” of a single classical world by all observers—is restored.

So it’s undetectable unless you can rearrange a whole cat to atomic precision.

So you can’t have coherent superpositions of macroscopic objects. So you need decoherence. And you need it to be simple, so that it is still a “slam dunk”.

Basically, blobs of amplitude need to run into each other to interact.

How narrow a quantum state is depends, like everything, on the choice of basis. What is sharply peaked in position space is spread out in frequency/momentum space.

Interaction with the environment is a straightforward application of schrodingers equation.

No it isn’t. That’s why people are still publishing papers on it.

TAG 22 Sep 2022 11:46 UTC
1 point
0 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

I don’t think there is one. I think it likely that the universe started in a coherent state, and it still is coherent

Then why don’t we see other universes, and why do we make only classical observations? Of course, these are the two problems with Everett’s original theory that prompted all the subsequent research. Coherent states continue to interact, so you need decoherence for causally separate, non interacting worlds...and you need to explain the preponderance of the classical basis, the basis problem.

Incoherence = entanglement with something else.

No, rather the reverse. It’s when off diagonal elements are zero or negligible.

Decoherence, the disappearance of a coherent superposed state, seems to occur when a particle interacts with macroscopiic apparatus or the environment. But thats also the evidence for collapse. You can’t tell directly that you’re dealing with decoherent splitting,rather than collapse because you can’t observe decoherent worlds.

TAG 21 Sep 2022 18:05 UTC
1 point
0 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

Quantum mechanics has a “branch both ways” that is sometimes mistaken for randomness. True randomness would be non-unitary and break a bunch of the maths.

Which is an odd things to say, since the maths used by Copenhagenists is identical to the maths used by many worlders.

It isn’t totally inconceivable that the universe does it anyway, but it seems unlikely. Do you have any coherent idea of what the universe might possibly do

You are trying to appeal to the Yudkowsky version of Deutsch as incontrovertible fact, and it isn’t.

If the MWI is so good, why do half of all physicists reject it?

If Everett’s 1957 thesis solved everything, why have there been decades of subsequent work?

Bearing in mind that evolution under the Schrodinger equation cannot turn a coherent state into an incoherent one, what is the mechanism of decoherence?

What is there a basis problem, and what solves it?

TAG 21 Sep 2022 17:50 UTC
2 points
1 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

The problem is that anything can be changed into anything, with enough changes.

Ok. Are you suggesting a better technical definition, or are you suggesting going back to the subjective approach?

It tests all possible sequences of actions in these simulations.

No it doesn’t.

If it needs to hack some robots, and break in to where it’s reward button is,

It doesn’t have one. An AIXI isn’t an learning system, and doesn’t have a reward function.

it will. If it needs to win a game of chess, it will.

An AIXI is an algorithm that tries to predict sequences of input data using programmes. That’s it. It doesnt want or need.

Are you claiming AIXI won’t do this. It will just sit there being dumb?

No, it will sit there figuring out the shortest code sequence that predicts its input. The only thing it can do.

Or are you claiming that however clever seeming it’s external behavior, it doesn’t count as a plan for some reason?

What external behaviour?

TAG 20 Sep 2022 17:20 UTC
3 points
0 ∶ 0
in reply to: Xen’s comment on: Prize idea: Transmit MIRI and Eliezer’s worldviews

a naturalist worldview as opposed to embedded agency

What’s the difference?

TAG 20 Sep 2022 17:18 UTC
1 point
0 ∶ 0
in reply to: Conor Sullivan’s comment on: Prize idea: Transmit MIRI and Eliezer’s worldviews
EY originally blamed failure to agree with his obviously correct arguments about AI on poor thinking skills, then set about to correct that. But other explanations are possible.

TAG 19 Sep 2022 18:51 UTC
1 point
0 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

Any optimizer needs to be optimizing for something.

OK, but you can’t infer that something is an optimiser from the fact that it’s good at something. You can infer that it’s optimising something if you can change the something.

The universe is deterministic.

Not a fact.

So this applies equally well to a human, AlphaChess and Deep blue

Not everything has a replaceable UF or goal module. That renders it false that every AI has a goal. That means that you can’t achieve general AI safety by considering goals alone.

Would you agree that AIXI-tl is just as hard coded as Deep Blue? And that nonetheless, it forms clever plans to achieve its goals and is very dangerou

No, AIXIs don’t form plans.

TAG 18 Sep 2022 17:42 UTC
1 point
0 ∶ 0
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

But there is no part of it that creates new plans of how to make toast better. An evolutionary search for aerial designs can come up with new shapes, better than anything a human could invent. Deep blue can invent new chess moves no human could think of. A toaster doesn’t invent a new better way of making toast.

Ok...but what is your point? That any optimiser has goals?

Can you explain what an AI that plays good chess, but not because it wants to win, would be like?

Any current chess software with the possible exception of AlphaChess.

A hard coded chess program wouldn’t be able to something else just because it wanted to.

TAG 18 Sep 2022 14:29 UTC
2 points
0 ∶ 0
in reply to: tailcalled’s comment on: Why are we sure that AI will “want” something?
Well, I already answered that question.

TAG 17 Sep 2022 19:00 UTC
1 point
0 ∶ 0
in reply to: tailcalled’s comment on: Why are we sure that AI will “want” something?
Superintelligences don’t necessarily have goals, and could arrive gradually. A jump to agentive, goal driven ASI is the worst case scenario, but it’s also conjunctive.

TAG 17 Sep 2022 17:25 UTC
1 point
0 ∶ 0
in reply to: tailcalled’s comment on: Why are we sure that AI will “want” something?

Can we come up with any nontrivial goals that it wouldn’t be a catastrophe to give to it?

We already have some systems with goals. They seem to mostly fail in the direction of wireheading, which is not catastrophic.

TAG 17 Sep 2022 14:34 UTC
1 point
0 ∶ 0
on: Why are we sure that AI will “want” something?

But why would it do something when not asked? I.e. Why would it have needs/wants/desires to do anything at all?

These are inequivalent, but the answer to each is “because it was designed that way”. Conventional software agents, which don’t have to be particularly intelligent, do things without being explicitly instructed.

TAG 17 Sep 2022 13:56 UTC
1 point
1 ∶ 2
in reply to: Donald Hobson’s comment on: Why are we sure that AI will “want” something?

Firstly we already have AI designs that “want” to do things. Deep blue “wanted” to win at chess. Various reinforcement learning agents that “want” to win other games.

“Wanting” in quotes isn’t the problem. Toasters “want” to make toast.

Intelligence that isn’t turned to doing anything is kind of useless. Like you have an AI that is supposedly very intelligent. But it sits there just outputting endless 0′s. What’s the point of that?

Doing something is not the same thing as doing-something-because-you-want-to. Toasters don’t want to make toast, in the un-scare-quoted sense, they just do. Having goals, aims and drives is only meaningful if they can be swapped out for other ones (even if through training). It’s a counterfactual concept.

TAG 17 Sep 2022 13:48 UTC
1 point
0 ∶ 0
in reply to: tailcalled’s comment on: Why are we sure that AI will “want” something?

But having strong, precise impacts in open-ended environments is closely related to consequentialism.

But consequentialism only means achieving some kind of goal: it doesn’t have to be a goal you are motivated by. If you are motivated to fulfil goals that are given to you , you can still “use consequentialism”.

TAG 16 Sep 2022 20:48 UTC
2 points
0 ∶ 0
in reply to: Signer’s comment on: Consciousness Actually Explained: EC Theory

I’m failing to understand your comment in context and need elaboration. My point was that you can’t use any property, except existence, as a reason for the absence of consciousness, because that property doesn’t change for humans in the zombie world

The whole point of zombie argument is that consciousness is or depends on a non physical property that can’t detected externally.