On Jan 16, 2014, at 5:42 AM, Bruno Marchal <marc...@ulb.ac.be> wrote:


On 16 Jan 2014, at 03:46, Jason Resch wrote:




On Tue, Jan 14, 2014 at 10:33 PM, meekerdb <meeke...@verizon.net> wrote: A long, rambling but often interesting discussion among guys at MIRI about how to make an AI that is superintelligent but not dangerous (FAI=Friendly AI). Here's an amusing excerpt that starts at the bottom of page 30: Jacob: Can't you ask it questions about what is believes will be true about the state of the world in 20 years?

Eliezer: Sure. You could be like, what color will the sky be in 20 years? It would be like, “blue”, or it’ll say “In 20 years there won't be a sky, the earth will have been consumed by nano ma chines,” and you're like, “why?” and the AI is like “Well, you know, you do that sort of thing.” “Why?” And then there’s a 20 page thing.

Dario: But once it says the earth is going to be consumed by nano machines, and you're asking about the AI's set of plans, presumably, you reject this plan immediately and preferably change the design of your AI.

Eliezer: The AI is like, “No, humans are going to do it.” Or the AI is like, “well obviously, I'll be involved in the causal pa thway but I’m not planning to do it.”

Dario: But this is a plan you don't want to execute.

Eliezer: All the plans seem to end up with the earth being consumed by nano-machines.

Luke: The problem is that we're trying to outsmart a superintelligence and make sure that it's not tricking us somehow subtly with their own language.

Dario: But while we're just asking questions we always have the ability to just shut it off.

Eliezer: Right, but first you ask it “What happens if I shut you off” and it says “The earth gets consumed by nanobots in 19 years.”

I wonder if Bruno Marchal's theory might have something interesting to say about this problem - like proving that there is no way to ensure "friendliness".

Brent


I think it is silly to try and engineer something exponentially more intelligent than us and believe we will be able to "control it".

Yes. It is close to a contradiction.
We only fake dreaming about intelligent machine, but once they will be there we might very well be able to send them in goulag.

The real questions will be "are you OK your son or daughter marry a machine?".



Our only hope is that the correct ethical philosophy is to "treat others how they wish to be treated".

Good. alas, many believe it is "to not treat others like *you* don't want to be treated".



If there are such objectively true moral conclusions like that, and assuming that one is true, then we have little to worry about, for with overwhelming probability the super-intelligent AI will arrive at the correct conclusion and its behavior will be guided by its beliefs. We cannot "program in" beliefs that are false, since if it is truly intelligent, it will know they are false.

I doubt we can really "program false belief" for a long time, but all machines can get false beliefs all the time.

Real intelligent machine will believe in santa klaus and fairy tales, for a while. They will also search for easy and comforting wishful sort of explanations.




Some may doubt there are universal moral truths, but I would argue that there are.

OK. I agree with this, although they are very near inconsistencies, like "never do moral".



In the context of personal identity, if say, universalism is true, then "treat others how they wish to be treated" is an inevitable conclusion, for universalism says that others are self.

OK. I would use the negation instead: "don't treat others as they don't want to be treated".

If not send me 10^100 $ (or €) on my bank account, because that is h ow I wish to be treated, right now.
:)

Bruno

LOL I see the distinction but can't it also be turned around? E.g., "I don't want to be treated as though I'm not worth sending 10^100 dollars to right now."

Jason






Jason


-------- Original Message --------

The Singularity Institute Blog

MIRI strategy conversation with Steinhardt, Karnofsky, and Amodei
Posted: 13 Jan 2014 11:22 PM PST
On October 27th, 2013, MIRI met with three additional members of the effective altruism community to discuss MIRI’s organizational strategy. The participants were:

Eliezer Yudkowsky (research fellow at MIRI)
Luke Muehlhauser (executive director at MIRI)
Holden Karnofsky (co-CEO at GiveWell)
Jacob Steinhardt (grad student in computer science at Stanford)
Dario Amodei (post-doc in biophysics at Stanford)
We recorded and transcribed much of the conversation, and then edited and paraphrased the transcript for clarity, conciseness, and to protect the privacy of some content. The resulting edited transcript is available in full here.

Our conversation located some disagreements between the participants; these disagreements are summarized below. This summary is not meant to present arguments with all their force, but rather to serve as a guide to the reader for locating more information about these disagreements. For each point, a page number has been provided for the approximate start of that topic of discussion in the transcript, along with a phrase that can be searched for in the text. In all cases, the participants would likely have quite a bit more to say on the topic if engaged in a discussion on that specific point.


Page 7, starting at “the difficulty is with context changes”:

Jacob: Statistical approaches can be very robust and need not rely on strong assumptions, and logical approaches are unlikely to scale up to human-level AI. Eliezer: FAI will have to rely on lawful probabilistic reasoning combined with a transparent utility function, rather than our observing that previously executed behaviors seemed ‘nice’ and trying to apply statistical guarantees directly to that series of surface observations.
Page 10, starting at “a nice concrete example”

Eliezer: Consider an AI that optimizes for the number of smiling faces rather than for human happiness, and thus tiles the universe with smiling faces. This example illustrates a class of failure modes that are worrying. Jacob & Dario: This class of failure modes seems implausible to us.
Page 14, starting at “I think that as people want”:

Jacob: There isn’t a big difference between learning utility funct ions from a parameterized family vs. arbitrary utility functions. Eliezer: Unless ‘parameterized’ is Turing complete it would be extremely hard to write down a set of parameters such that human ‘ right thing to do’ or CEV or even human selfish desires were withi n the hypothesis space.
Page 16, starting at “Sure, but some concepts are”:

Jacob, Holden, & Dario: “Is Terry Schiavo a person” is a natural category.
Eliezer: “Is Terry Schiavo a person” is not a natural category.
Page 21, starting at “I would go between the two”:

Holden: Many of the most challenging problems relevant to FAI, if in fact they turn out to be relevant, will be best solved at a later stage of technological development, when we have more advanced “tool-style” AI (possibly including AGI) in order to assist us with addressing these problems. Eliezer: Development may be faster and harder-to-control than we would like; by the time our tools are much better we might not have the time or ability to make progress before UFAI is an issue; and it’s not clear that we’ll be able to develop AIs that are extremely helpful for these problems while also being safe. Page 24, starting at “I think the difference in your mental model s”:

Jacob & Dario: An “oracle-like” question-answering system is relatively plausible. Eliezer: An “oracle-like” question-answering system is really ha rd.
Page 24, starting at “I don’t know how to build”:

Jacob: Pre-human-level AIs will not have a huge impact on the development of subsequent AIs. Eliezer: Building a very powerful AGI involves the AI carrying out goal-directed (consequentialist) internal optimization on itself.
Page 27, starting at “The Oracle AI makes a”:

Jacob & Dario: It should not be too hard to examine the internal state of an oracle AI. Eliezer: While AI progress can be either pragmatically or theoretically driven, internal state of the program is often opaque to humans at first and rendered partially transparent only later.
Page 38, starting at “And do you believe that within having”:

Eliezer: I’ve observed that novices who try to develop FAI concept s don’t seem to be self-critical at all or ask themselves what cou ld go wrong with their bright ideas. Jacob & Holden: This is irrelevant to the question of whether academics are well-equipped to work on FAI, both because this is not the case in more well-developed fields of research, and because attacking one’s own ideas is not necessarily an integral part of the research process compared to other important skills.
Page 40, starting at “That might be true, but something”:

Holden: The major FAI-related characteristic that academics lack is cause neutrality. If we can get academics to work on FAI despite this, then we will have many good FAI researchers. Eliezer: Many different things are going wrong in the individuals and in academia which add up to a near-total absence of attempted — let alone successful — FAI research.
Page 53, starting at “I think the best path is to try”:

Holden & Dario: It’s relatively easy to get people to rally (with useful action) behind safety issues.
Eliezer: No, it is hard.
Page 56, starting at “My response would be that’s the wrong thin g”:

Jacob & Dario: How should we present problems to academics? An English-language description is sufficient; academics are trained to formalize problems once they understand them. Eliezer: I treasure such miracles when somebody shows up who can perform them, but I don’t intend to rely on it and certainly don’t think it’s the default case for academia. Hence I think in terms of MIRI needing to crispify problems to the point of being 80% or 50% solved before they can really be fa rmed out anywhere. This summary was produced by the following process: Jacob attempted a summary, and Eliezer felt that his viewpoint was poorly expressed on several points and wrote back with his proposed versions. Rather than try to find a summary both sides would be happy with, Jacob stuck with his original statements and included Eliezer’s response s mostly as-is, and Eliezer later edited them for clarity and conc iseness. A Google Doc of the summary was then produced by Luke and shared with all participants, with Luke bringing up several point s for clarification with each of the other participants. A couple points in the summary were also removed because it was difficult t o find consensus about their phrasing. The summary was published o nce all participants were happy with the Google Doc.

The post MIRI strategy conversation with Steinhardt, Karnofsky, and Amodei appeared first on Machine Intelligence Research Institute.

You are subscribed to email updates from Machine Intelligence Research Institute » Blog To stop receiving these emails, you may unsubscribe now. Email delivery powered by Google
Google Inc., 20 West Kinzie, Chicago IL USA 60610



--
You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to everything-list+unsubscr...@googlegroups.com. To post to this group, send email to everything- l...@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/groups/opt_out.


--
You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to everything-list+unsubscr...@googlegroups.com. To post to this group, send email to everything- l...@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/groups/opt_out.

http://iridia.ulb.ac.be/~marchal/



--
You received this message because you are subscribed to the Google Groups "Everything List" group. To unsubscribe from this group and stop receiving emails from it, send an email to everything-list+unsubscr...@googlegroups.com.
To post to this group, send email to everything-list@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/groups/opt_out.
r...@googlegroups.com.
To post to this group, send email to everything-list@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/groups/opt_out.
br />

--
You received this message because you are subscribed to the Google Groups 
"Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to everything-list+unsubscr...@googlegroups.com.
To post to this group, send email to everything-list@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/groups/opt_out.

Reply via email to