All of arbimote's Comments + Replies

EDIT: The original post now has updated times and links, so refer to that instead.

Here are links to the times suggested, for convenience:

• New York City: Fridays at 1pm
• Paris: Tuesdays at 1pm
• San Francisco: Wednesdays at 1pm
• Melbourne: Tuesdays at 9pm (edited to actually coincide with Paris)

I'd suggest posting meeting times using timeanddate.com, to help avoid confusion about time zones and daylight savings.

Perhaps what is missing is these rules:

AT = A (1)

AF = F (2)

A + T = T (3)

A + F = A (4)

Which can be derived from the given axioms, apparently. I'm not sure if some necessary axioms were omitted.

Using some of these, here's one way to derive B!A=!A from !B=AD:

!B = AD

!B + A = AD + A

!B + A = AD + AT (1)

!B + A = A(D + T) (Distributivity)

!B + A = AT (3)

!B + A = A (1)

!!B!A = !A (Duality)

B!A = !A

I'm in.

Post also mentioned Tolerate Tolerance

Hi.

I registered and started posting a while back, but since then have reverted to lurking. Partly due to not having time, but I can also identify with reasons some others have given.

Voted down for being off-topic.

Verifying a proof is quite a bit simpler that coming up with the proof in the first place.

Perhaps keep anonymous votes too, but make them worth less or only use them to break ties.

A sequence of wins and non-wins is enough to tell you whether a given approach can result in intelligent behaviour. That alone is enough to make it a useful experiment.

A man with one watch might have the wrong time; a man with two watches is more aware of his own ignorance.

The basement is the biggest

I like that turn of phrase.

I was about to point out that the fascinating and horrible dynamics of over-the-top threats are covered in length in Strategy of Conflict. But then I realised you're the one who made that post in the first place. Thanks, I enjoyed that book.

It's much easier to limit output than input, since the source code of the AI itself provide it with some patchy "input" about what the external world is like. So there is always some input, even if you do not allow human input at run-time.

ETA: I think I misinterpreted your comment. I agree that input should not be unrestricted.

You sir, have made a gender assumption.

Similar topics were discussed in an Open Thread.

Luckily digital constructs are easier to perfect that wooden ones. Although you wouldn't think so with the current state of most software.

It is difficult to constrain the input we give to the AI, but the output can be constrained severely. A smart guy could wake up alone in a room and infer how he evolved, but so long as his only link to the outside world is a light switch that can only be switched once, there is no risk that he will escape.

If Dave holds a consequentialist ethical theory that only values his own life, then yes we are screwed.

If Dave's consequentialism is about maximizing something external to himself (like the probable state of the universe in the future, regardless of whether he is in it), then his decision has little or no weight if he is a simulation, but massive weight if he is the real Dave. So the expected value of his decision is dominated by the possibility of him being real.

If we accept the simulation hypothesis, then there are already gzillions of copies of us, being simulated under a wide variety of torture conditions (and other conditions, but torture seems to be the theme here). An extortionist in our world can only create a relatively small number of simulations of us, relatively small enough that it is not worth taking them into account. The distribution of simulation types in this world bears no relation to the distribution of simulations we could possibly be in.

If we want to gain information about what sort of simul... (read more)

Here's an idea for how a LW-based commercial polling website could operate. Basically it is a variation on PredictionBook with a business model similar to TopCoder.

The website has business clients, and a large number of "forecasters" who have accounts on the website. Clients pay to have their questions added to the website, and forecasters give their probability estimates for whichever questions they like. Once the answer to a question has been verified, each forecaster is financially rewarded using some proper scoring rule. The more money as... (read more)

Perhaps start by giving it away, or sell it to small buyers (eg. individuals).

But I've got to admit I don't have experience in this area, so my suggestions are mostly naive speculation (but hopefully my speculation is of high quality!). Research into existing prediction companies is called for.

If we are the kind of people who would delete lots of AIs, I don't see why AIs would not see it as similarly ethical to delete lots of us.

So just in case we are a simulated AI's simulation of its creators, we should not simulate an AI in a way it might not like? That's 3 levels of a very specific simulation hypothesis. Is there some property of our universe that suggests to you that this particular scenario is likely? For the purpose of seriously considering the simulation hypothesis and how to respond to it, we should make as few assumptions as poss... (read more)

I'm concerned about the moral implications of creating intelligent beings with the intent of destroying them after they have served our needs [...]

Personally, I would rather be purposefully brought into existence for some limited time than to never exist at all, especially if my short life was enjoyable.

I evaluate the morality of possible AI experiments in a consequentialist way. If choosing to perform AI experiments significantly increases the likelihood of reaching our goals in this world, it is worth considering. The experiences of one sentient AI ... (read more)

I merely wanted to point out to Kaj that some "meaningful testing" could be done, even if the simulated world was drastically different from ours. I suspect that some core properties of intelligence would be the same regardless of what sort of world it existed in - so we are not crippling the AI by putting it in a world removed from our own.

Perhaps "if released into our world" wasn't the best choice of words... more likely, you would want to use the simulated AI as an empirical test of some design ideas, which could then be used in a separate AI being carefully designed to be friendly to our world.

People would hire the firm if it could be demonstrated that the firm consistently produced accurate results. So initial interest might be low, but pick up over time as the track record gets longer.

You could observe how it acts in its simulated world, and hope it would act in a similar way if released into our world. ETA: Also, see my reply for possible single-bit tests.

I have had some similar thoughts.

The AI box experiment argues that a "test AI" will be able to escape even if it has no I/O (input/output) other than a channel of communication with a human. So we conclude that this is not a secure enough restraint. Eliezer seems to argue that it is best not to create an AI testbed at all - instead get it right the first time.

But I can think of other variations on an AI box that are more strict than human-communication, but less strict than no-test-AI-at-all. The strictest such example would be an AI simulatio... (read more)

I personally don't mind "tl;dr", but I agree that where practical it is best to use language that will be understood by as wide an audience as possible. (Start using "tl;dr" again when it becomes mainstream :) )

Are extensional and intensional definitions related to outside views and inside views? I suppose extensional definitions and outside view are about drawing conclusions from a class of things, while the intensional and inside use specific details more unique to the thing in question.

I agree with the gist of your post, but this paragraph:

Conversely, we know the LHC is not going to destroy the world, because nature has been banging particles together at much higher energy levels for billions of years...

is a common argument, that doesn't really stand up once you take into account anthropic bias.

Saying "oh sorry I hurt your feelings" is just plain being nice, which is a good idea whether you are aiming to be rational or not.

Someone actually made a top-level post on this the other day. Just sayin'.

You can have emotions while being rational, and you can be rational while having emotions. They are opposed sometimes, but they do not always have to be. But when there is a conflict between them, rationality (so long as you practice it properly) is more reliable in reaching correct, useful conclusions.

It would be great for this rationalist community to be able to discuss any topic, but in a way that insulates the main rationality discussions from off-topic discussions. Perhaps forum software separate from the main format of LessWrong? Are monthly open threads enough for off-topic discussions?

Add a term granting a large disutility for deaths, and this should do the trick.

What if death isn't well-defined? What if the AI has the option of cryonically freezing a person to save their life - but then being frozen, that person does not have any "current" utility function, so the AI can then disregard them completely. Situations like this also demonstrate that more generally, trying to satisfy someone's utility function may have an unavoidable side-effect of changing their utility function. These side-effects may be complex enough that... (read more)

I sent an email on January the 10th, and haven't yet got a reply. Has my email made it to you? Granted, it is over a month since this article was posted, so I understand if you are working on things other than applications at this point...

Or to take an open source term, "Benevolent Dictator for Life".

If there is, I'd like to know too, for when(/if) I try my hand at a top-level post. Hopefully the rating and moderation system is good enough such that no formal rule is needed.

Or the two are fairly independent - you can be good or bad at seeking status, intelligent or not-so intelligent, and it is possible to have any combination of those, including that of being unintelligent and yet still good at obtaining status.

Yes

That claims of this type are sometimes made to advance agendas does not mean we shouldn't make these claims, or that all such claims are false. It means such claims need to be scrutinised more carefully.

I agree that more often than not there is not a simple solution, and people often accept a false simple solution too readily. But the absence of a simple solution does not mean there is no theoretical optimal strategy for continually working through the difficulty.

I agree with the message of the article, but I do not think it is forever going to be impossible to query what science currently knows.

Improvements in search technology cause a decrease in the time taken to do a reasonable search for any existing knowledge on a topic. Before the internet you might have had to read dozens of journals to have a vague idea of whether a field had discovered something in particular. Now you can do an online search. Conceivably, a future search engine could be good enough that it could take some imprecise (non-jargon) search ... (read more)

... seems to have this belief that there is some perfect cure for any problem.

There may not be a single strategy that is perfect on it's own, but there will always be an optimum course of action, which may be a mixture of strategies (eg dump $X into nanotech safety, $Y into intelligence enhancement, and $Z into AGI development). You might never have enough information to know the optimal strategy to maximise your utility function, but one still exists, and it is worth trying to estimate it.

I mention this because previously I have heard "there is n... (read more)

For some things (especially concrete things like animals or toothpaste products), it is easy to find a useful reference class, while for other things it is difficult to find which possible reference class, if any, is useful. Some things just do not fit nicely enough into an existing reference class to make the method useful - they are unclassreferencable, and it is unlikely to be worth the effort attempting to use the method, when you could just look at more specific details instead. ("Unclassreferencable" suggests a dichotomy, but it's more of... (read more)

• Handle: arbimote
• Gender: Male
• Age: 22 (born 1987)
• Location: Australia
• Occupation: Student of computer science

I've been lurking since May 2009. My views on some issues that are often brought up on LW are:

• It's a good idea to sign up to cryonics if you have the money, due to a Pascal's Wager type argument. I have not signed up, since I do not yet have the money (and AFAIK there are further complications due to being in Australia).
• It is possible and desirable for humans to create AGI.
• MWI seems intuitive to me, but I have not read enough about the subj