gedymin

Karma: 199

gedymin Jan 4, 2015, 9:01 PM
1 point
in reply to: skeptical_lurker’s comment on: Brain-centredness and mind uploading
We usually don’t worry about personality changes because they’re typically quite limited. Completely replacing brain biochemistry would be a change on a completely different scale.

And people occasionally do worry about these changes even now, especially if they’re permanent, and if/when they occur in others. Some divorces are made because the partner of a person “does not see the same man/woman she/he fell in love with”.

gedymin Jan 4, 2015, 1:02 PM
4 points
in reply to: Viliam_Bur’s comment on: Open thread, Dec. 29, 2014 - Jan 04, 2015
Taxing the upper middle class is a generally good idea; they are the ones most capable and willing to pay taxes. Many European countries apply progressive tax rates. Calling it a millionanaire tax is a misnomer, or course, but otherwise I would support that (I’m from Latvia FYI)

Michael O. Church is certainly an interesting writer, but you should take into account that he basically is a programmer with no academic qualifications. Most of his posts appear to be wild generalizations of experiences personally familiar to him. (Not exclusively his own experiences, of course.) I suspect that he suffers heavily from the narrative fallacy.

gedymin Jan 2, 2015, 6:04 PM
2 points
in reply to: richard_reitz’s comment on: Stupid Questions January 2015
A good writeup. But you downplay the role of individual attention. No textbook is going to have all the answers to questions someone might formulate after reading the material. They also won’t provide help to students who get stuck doing exercises. In books, it’s either nothing or all (the complete solution).

The current system does not do a lot of personalized teaching because the average university has a tightly limited amount of resources per student. The very rich universities (such as Oxford) can afford to give a training personalized to a much larger extent, via tutors.

Brain-centredness and mind uploading

gedyminJan 2, 2015, 12:23 PM

24 points

2 comments3 min readLW link

gedymin Jan 1, 2015, 5:22 PM
5 points
on: Stupid Questions January 2015
What are some good examples of rationality as “systematized winning”? E.g. a personal example of someone who practices rationality systematically for a long time, and there are good reasons to think doing that has substantially improved their life.

It’s easy to name a lot of famous examples where irrationally has caused harm. I’m looking for the opposite. Ideally, some stories that could interest intelligent, but practically minded people who have no previous exposure to the LW memeplex.

gedymin Jan 1, 2015, 11:31 AM
6 points
in reply to: blogospheroid’s comment on: Stupid Questions January 2015
The answer to the specific question about technetium is “it’s complicated, and we may not know yet”, according to physics Stack Exchange.

For the general question “why are some elements/isotopes less or more stable”—generally an isotope is more stable if it has a balanced number of protons and neutrons .

gedymin Dec 31, 2014, 2:41 PM
0 points
in reply to: Plasmon’s comment on: Open thread, Dec. 29, 2014 - Jan 04, 2015
I know what SI is. I’m not even pushing the point that SI not always the best thing to do—I’m not sure if it is, as it’s certainly not free of assumptions (such as the choice of the programming language / Turing machine), but let’s not go into that discussion.

The point I’m making is different. Imagine a world / universe where nobody has any idea what SI is. Would you be prepared to speak to them, all their scientists, empiricists and thinkers and say that “all your knowledge is purely accidental, you unfortunately have absolutely no methods for determining what the truth is, no reliable methods to sort out unlikely hypotheses from likely ones - while we, incidentally, do have the method and it’s called Solomonoff induction”? Because it looks like what iarwain1 is saying implies that. I’m sceptical of this claim.

gedymin Dec 31, 2014, 12:52 PM
1 point
in reply to: Plasmon’s comment on: Open thread, Dec. 29, 2014 - Jan 04, 2015
Let me clarify my question. Why do you and iarwain1 think there are absolutely no other methods that can be used to arrive at the truth, even if they are sub-optimal ones?

gedymin Dec 31, 2014, 10:29 AM
1 point
in reply to: iarwain1’s comment on: Open thread, Dec. 29, 2014 - Jan 04, 2015
Why can’t there be other criteria to prefer some theories over other theories, besides simplicity?

gedymin Dec 31, 2014, 10:22 AM
0 points
in reply to: passive_fist’s comment on: Open thread, Dec. 29, 2014 - Jan 04, 2015
Perhaps you can comment this opinion that “simpler models are always more likely” is false: http://www2.denizyuret.com/ref/domingos/www.cs.washington.edu/homes/pedrod/papers/dmkd99.pdf

gedymin Dec 30, 2014, 7:11 PM
5 points
in reply to: KatjaGrace’s comment on: Superintelligence 16: Tool AIs
Perhaps one could say that an agent in the sense that matters for this discussion is something with a personal identity, a notion of self (in a very loose sense).

Intuitively, it seems that tool AIs are safer because they are much more transparent. When I run a modern general purpose constraint-solver tool, I’m pretty sure that no AI agent will emerge during the search process. When I pause the tool somewhere in the middle of the search and examine its state, I can predict exactly what the next steps are going to be—even though I can hardly predict the ultimate result of the search!

In contrast, the actions of an agent are influenced by its long-term state (it’s “personality”), so its algorithm is not straightforward to predict.

I feel that the only search processes capable of internally generating agents (the thing Bostrom is worried about) are the ones insufficiently transparent (e.g. ones using neural nets).

gedymin Dec 28, 2014, 12:37 PM
4 points
on: The buildup to Jaynes?
See this discussion in The Best Textbooks on Every Subject

I agree that the first few chapters of Jaynes are illuminating, haven’t tried to read further. Bayesian Data Analysis by Gelman feels much more practical at least for what I personally need (a reference book for statistical techniques).

The general pre-requisites are actually spelled out in the introduction of Jayne’s Probability Theory. Emphasis mine.

The following material is addressed to readers who are already familiar with applied mathematics at the advanced undergraduate level or preferably higher; and with some field, such as physics, chemistry, biology, geology, medicine, economics, sociology, engineering, operations research, etc., where inference is needed. A previous acquaintance with probability and statistics is not necessary; indeed, a certain amount of innocence in this area may be desirable, because there will be less to unlearn.

gedymin Dec 25, 2014, 1:01 PM
9 points
in reply to: Nikario’s comment on: Open thread, Dec. 22 - Dec. 28, 2014
Scott Aaronson has formulated it in a similar way (quoted from here):

whenever it’s been possible to make definite progress on ancient philosophical problems, such progress has almost always involved a [kind of] “bait-and-switch.” In other words: one replaces an unanswerable philosophical riddle Q by a “merely” scientific or mathematical question Q′, which captures part of what people have wanted to know when they’ve asked Q. Then, with luck, one solves Q′.

Of course, even if Q′ is solved, centuries later philosophers might still be debating the exact relation between Q and Q′! And further exploration might lead to other scientific or mathematical questions — Q′′, Q′′′, and so on — which capture aspects of Q that Q′ left untouched. But from my perspective, this process of “breaking oﬀ” answerable parts of unanswerable riddles, then trying to answer those parts, is the closest thing to philosophical progress that there is.

…A good replacement question Q′ should satisfy two properties: (a) Q′ should capture some aspect of the original question Q — so that an answer to Q′ would be hard to ignore in any subsequent discussion of Q, [and] (b) Q′ should be precise enough that one can see what it would mean to make progress on Q′: what experiments one would need to do, what theorems one would need to prove, etc.

gedymin Dec 25, 2014, 11:50 AM
2 points
in reply to: KatjaGrace’s comment on: Superintelligence 15: Oracles, genies and sovereigns
In human society and at the highest scale, we solve the agent-principal problem by separation of powers—legislative, executive, and judiciary powers of state typically are divided in independent branches. This naturally leads to a categorization of AI-capabilities:
- AI with legislative power (the power to make new rules)
- AI with with high-level executive power (the power to make decisions)
- AI with with low-level executive power (to carry out orders)
- AI with a rule-enforcing power
- AI with a power to create new knowledge / make suggestions for decisions
What Bostrom & co shows is that the seemingly innocent powers to create new knownledge and carry out low-level, well-specified tasks are in fact very unsafe. (The Riemann’s hypothesis solver, the paperclip maximizer).

What Bostrom implicitly assumes is that the higher levels of powers do not bring any important new dangers, and might, in fact, be better for the humanity. (The example of an all-powerful sovereign that decides and enforces moral laws in a way that makes them similar to physical laws.) I feel that this point requires more analysis. In general, each new capability brings more ways how to be unfriendly.

gedymin Dec 24, 2014, 4:49 PM
4 points
in reply to: skeptical_lurker’s comment on: LINK: Nematode brain uploaded with success
I don’t know about the power needed to simulate the neurons, but my guess is that most of the resources are spent not on the calculations, but on interprocess communication. Running 302 processes on a Raspberry Pi and keeping hundreds of UDP sockets open probably takes a lot of its resources.

The technical solution is neither innovative nor fast. The benefits are in its distributed nature (every neuron could be simulated on a different computer) and in simplicity of implementation. At least while 100% faithfullness to the underlying mathematical model is not required. I have no idea how the author plans to avoid unintended data loss in the not-unusual case when some UDP packets are dropped. Retransmission (TCP) is not really an option either, as the system has to run in real time.

gedymin Dec 24, 2014, 4:32 PM
8 points
on: LINK: Nematode brain uploaded with success
http://lesswrong.com/r/discussion/lw/lah/link_simulating_c_elegans/

gedymin Dec 23, 2014, 8:33 PM
5 points
on: Superintelligence 15: Oracles, genies and sovereigns
It would be interesting to see more examples of modern-day non-superintelligent domain-specific analogues of genies, sovereigns and oracles, and to look at their risks and failure modes. Admittedly, this is only an inductive evidence that does not take into account the qualitative leap between them and superintelligence, but it may be better than nothing. Here are some quick ideas (do you agree with the classification?):
- Oracles—pocket calculators (Bostrom’s example); Google search engine; decision support systems.
- Genies—industrial robots; GPS driving assistants.
- Sovereigns—automated trading systems; self-driving cars.
The failures of automated trading systems are well-known and have cost hundreds of millions of dollars. On the other hand, the failures of human bankers who used ill-suited mathematical models for financial risk estimation are also well-known (the recent global crisis), and may have host hundreds of billions of dollars.

gedymin 23 Dec 2014 20:30 UTC
1 point
in reply to: KatjaGrace’s comment on: Superintelligence 15: Oracles, genies and sovereigns
It’s ok, as long as the talking is done in sufficiently rigorous manner. By an analogy, a lot of discoveries in theoretical physics have been made long before they could be experimentally supported. Theoretical CS also has good track record here, for example, the first notable quantum algorithms were discovered long before the first notable quantum computers were built. Furthermore, the theory of computability mostly talks about the uncomputable (computations that cannot be realized and devices that cannot be built in this universe), so has next to no practical applications. It just so happened that many of the ideas and methods developed for CT also turned out to be useful for its younger sister—the theory of algorithmic complexity, which has enormous practical importance.

In short, I feel that the quality of an academic inquiry is more dependent on its methods and results than on its topic.

gedymin 23 Dec 2014 20:29 UTC
2 points
in reply to: KatjaGrace’s comment on: Superintelligence 15: Oracles, genies and sovereigns
To be honest, I initially had trouble understanding your use of “oversight” and had to look up the word in a dictionary. Talking about the different levels of executive power given to AI agents would make more sense to me.

gedymin 20 Dec 2014 11:59 UTC
1 point
in reply to: alienist’s comment on: Velocity of behavioral evolution
I agree. For example, this page says that: “in order to provide a convincing case for epigenetic inheritance, an epigenetic change must be observed in the 4th generation. ”

So I wonder why they only tested three generations. Since F1 females are already born with the reproductive cells from which F2 will grow, the organism of a F0 exposes both of these future generations to itself and its environment. That some information exchange takes place there is not that surprising, but the effect may be completely lost in F3 generation.

gedymin

Brain-cen­tred­ness and mind uploading

Brain-centredness and mind uploading