I must admit I can’t make any sense of your objections. There aren’t any deep philosophical issues with understanding decision algorithms from an outside perspective. That’s the normal case! For instance, A*
nshepperd
Karma: 1,900
This isn’t a criticism of this post or of Vaniver, but more a comment on Circling in general prompted by it. This example struck me in particular:
Orient towards your impressions and emotions and stories as being yours, instead of about the external world. “I feel alone” instead of “you betrayed me.”
It strikes me as very disturbing that this should be the example that comes to mind. It seems clear to me that one should not, under any circumstances engage in a group therapy exercise designed to lower your emotional barriers and create vulnerability in the presence of anyone you trust less than 100%, let alone someone you think has ‘betrayed’ you. This seems like a great way to get manipulated, taken advantage of by sexual abusers, gaslighted etc, which is a particular concern given the multiple allegations of abuse and sexual misconduct in the EA/Circling communities (1, 2, ChristianKl’s comment). Reframing these behaviours as personal emotions and stories seems like it would further contribute to the potential for such abuse.
Where does that obligation come from?
This may not be Said’s view, but it seems to me that this obligation comes from the sheer brute fact that if no satisfactory response is provided, readers will (as seems epistemically and instrumentally correct) conclude that there is no satisfactory response and judge the post accordingly. (Edit: And also, entirely separately, the fact that if these questions aren’t answered the post author will have failed to communicate, rather defeating the point of making a public post.)
Obviously readers will conclude this more strongly if there’s a back-and-forth in which the question is not directly answered, and less strongly if the author doesn’t respond to any comments at all (which suggests they’re just busy). (And readers will not conclude this at all if the question seems irrelevant or otherwise not to need a response.)
That is to say, the respect of readers on this site is not automatically deserved, and cannot be taken by force. Replying to pertinent questions asking for clarification with a satisfactory response that fills a hole in the post’s logic is part of how one earns such respect; it is instrumentally obligatory.
On this view, preventing people from asking questions can do nothing but mislead readers by preventing them from noticing whatever unclearness / ambiguity etc the question would have asked about. It doesn’t release authors from this obligation, but just means we have to downgrade our trust in all posts on the site since this obligation cannot be met.
T3t’s explanations seem quite useless to me. The procedure they describe seems highly unlikely to reach anything like a correct interpretation of anything, being basically a random walk in concept space.
It’s hard to see what “I don’t understand what you meant by X, also here’s a set of completely wrong definitions I arrived at by free association starting at X” could possibly add over “I don’t understand what you meant by X”, apart from wasting everyone’s time redirecting attention onto a priori wrong interpretations.
I’m also somewhat alarmed to see people on this site advocating the sort of reasoning by superficial analogy we see here:
“Conforming to or based on fact” feels very similar to “the map corresponds to the territory”.
Performing the substitution: “An expression that is worthy of acceptance or belief, as the expression (map) corresponds to the internal state of the agent that generated it (territory).”
So, overall, I’m not very impressed, no.
But my sense is that if the goal of these comments is to reveal ignorance, it just seems better to me to argue for an explicit hypothesis of ignorance, or a mistake in the post.
My sense is the exact opposite. It seems better to act so as to provide concrete evidence of a problem with a post, which stands on its own, than to provide an argument for a problem existing, which can be easily dismissed (ie. show, don’t tell). Especially when your epistemic state is that a problem may not exist, as is the case when you ask a clarifying question and are yet to receive the answer!
To be clear, I think your comment was still net-negative for the thread, and provided little value (in particular in the presence of other commenters who asked the relevant questions in a, from my perspective, much more productive way)
I just want to note that my comment wouldn’t have come about were it not for Said’s.
Again, this is a problem that would easily be resolved by tone-of-voice in the real world, but since we are dealing with text-based communication here, these kinds of confusions can happen again and again.
To be frank, I find your attitude here rather baffling. The only person in this thread who interpreted Said’s original comment as an attack seems to have been you. Vaniver had no trouble posting a response, and agreed that an explanation was necessary but missing.
FWIW, that wasn’t my interpretation of quanticle’s comment at all. My reading is that “healthy” was not meant as a proposed interpretation of “authentic” but as an illustrative substitution demonstrating the content-freeness of this use of the word—because the post doesn’t get any more or less convincing when you replace “authentic” with different words.
This is similar to what EY does in Applause Lights itself, where he replaces words with their opposites to demonstrate that sentences are uninformative.
(As an interpretation, it would also be rather barren, and not particularly ‘concrete’ either: obviously “‘authentic’ means ‘healthy’” just raises the question of what ‘healthy’ means in this context!)
Why should “that which can be destroyed by the truth” be destroyed? Because the truth is fundamentally more real and valuable than what it replaces, which must be implemented on a deeper level than “what my current beliefs think.” Similarly, why should “that which can be destroyed by authenticity” be destroyed? Because authenticity is fundamentally more real and valuable than what it replaces, which must be implemented on a deeper level than “what my current beliefs think.” I don’t mean to pitch ‘radical honesty’ here, or other sorts of excessive openness; authentic relationships include distance and walls and politeness and flexible preferences.
To expand on Said and quanticle’s comments here, I find this argument deeply unconvincing, and here’s why. I see three things missing here:
A definition of ‘authentic’ in concrete terms—what kind of behaviour does it entail, with what kind of consequences? This can be a dictionary definition, in exchange for shifting a lot of burden to the following two steps.
An argument that ‘authenticity’ so defined is “real and valuable” enough to be more valuable than anything that might be lost in the course of such behaviour—this is not as simple as a superficial argument by analogy to truth might make it appear, since the argument for believing true things is more complex than that in the first place (for instance, relying on the particular role of true beliefs in decision theory).
An argument that Circling is ‘authentic’ in the manner so defined (presumably, since a defense of Circling seems to be the point of the post).
Currently all three holes here seem to be plugged by the simple use of ‘authentic’ as an applause light.
- Circling as Cousin to Rationality by (1 Jan 2020 1:16 UTC; 72 points)
- Circling as Cousin to Rationality by (1 Jan 2020 1:16 UTC; 72 points)
- 's comment on Meta-discussion from “Circling as Cousin to Rationality” by (2 Jan 2020 0:02 UTC; 48 points)
- 's comment on Meta-discussion from “Circling as Cousin to Rationality” by (2 Jan 2020 17:43 UTC; 22 points)
- 's comment on Meta-discussion from “Circling as Cousin to Rationality” by (2 Jan 2020 19:25 UTC; 18 points)
- 's comment on Meta-discussion from “Circling as Cousin to Rationality” by (1 Jan 2020 17:29 UTC; 15 points)
If what you want is to do the right thing, there’s no conflict here.
Conversely, if you don’t want to do the right thing, maybe it would be prudent to reconsider doing it...?
I don’t see the usual commonsense understanding of “values” (or the understanding used in economics or ethics) as relying on values being ontologically fundamental in any way, though. But you’ve the fact that they’re not to make a seemingly unjustified rhetorical leap to “values are just habituations or patterns of action”, which just doesn’t seem to be true.
Most importantly, because the “values” that people are concerned with then they talk about “value drift” are idealized values (ala. extrapolated volition), not instantaneous values or opinions or habituations.
For instance, philosophers such as EY consider that changing one’s mind in response to a new moral argument is not value drift because it preserves one’s idealized values, and that it is generally instrumentally positive because (if it brings one’s instantaneous opinions closer to their idealized values) it makes one better at accomplishing their idealized values. So indeed, we should let the EAs “drift” in that sense.
On the other hand, getting hit with a cosmic ray which alters your brain, or getting hacked by a remote code execution exploit is value drift because it does not preserve one’s idealized values (and is therefore bad, according to the usual decision theoretic argument, because it makes you worse at accomplishing them). And those are the kind of problems we worry about with AI.
When we talk of values as nouns, we are talking about the values that people have, express, find, embrace, and so on. For example, a person might say that altruism is one of their values. But what would it mean to “have” altruism as a value or for it to be one of one’s values? What is the thing possessed or of one in this case? Can you grab altruism and hold onto it, or find it in the mind cleanly separated from other thoughts?
Since this appears to be a crux of your whole (fallacious, in my opinion) argument, I’m going to start by just criticizing this point. This argument proves far too much. It proves that:
People don’t have beliefs, memories or skills
Books don’t have concepts
Objects don’t have colors
Shapes don’t have total internal angles
It seems as if you’ve rhetorically denied the existence of any abstract properties whatsoever, for the purpose of minimizing values as being “merely” habituations or patterns of action. But I don’t see why anyone should actually accept that claim.
Doesn’t it mean the same thing in either case? Either way, I don’t know which way the coin will land or has landed, and I have some odds at which I’ll be willing to make a bet. I don’t see the problem.
(Though my willingness to bet at all will generally go down over time in the “already flipped” case, due to the increasing possibility that whoever is offering the bet somehow looked at the coin in the intervening time.)
The idea that “probability” is some preexisting thing that needs to be “interpreted” as something always seemed a little bit backwards to me. Isn’t it more straightforward to say:
Beliefs exist, and obey the Kolmogorov axioms (at least, “correct” beliefs do, as formalized by generalizations of logic (Cox’s theorem), or by possible-world-counting). This is what we refer to as “bayesian probabilities”, and code into AIs when we want to them to represent beliefs.
Measures over imaginary event classes / ensembles also obey the Kolmogorov axioms. “Frequentist probabilities” fall into this category.
Personally I mostly think about #1 because I’m interested in figuring out what I should believe, not about frequencies in arbitrary ensembles. But the fact is that both of these obey the same “probability” axioms, the Kolmogorov axioms. Denying one or the other because “probability” must be “interpreted” as exclusively either #1 or #2 is simply wrong (but that’s what frequentists effectively do when they loudly shout that you “can’t” apply probability to beliefs).
Now, sometimes you do need to interpret “probability” as something—in the specific case where someone else makes an utterance containing the word “probability” and you want to figure out what they meant. But the answer there is probably that in many cases people don’t even distinguish between #1 and #2, because they’ll only commit to a specific number when there’s a convenient instance of #2 that make #1 easy to calculate. For instance, saying 1⁄6 for a roll of a “fair” die.
People often act as though their utterances about probability refer to #1 though. For instance when they misinterpret p-values as the post-data probability of the null hypothesis and go around believing that the effect is real...
No, that doesn’t work. It seems to me you’ve confused yourself by constructing a fake symmetry between these problems. It wouldn’t make any sense for Omega to “predict” whether you choose both boxes in Newcomb’s if Newcomb’s were equivalent to something that doesn’t involve choosing boxes.
More explicitly:
Newcomb’s Problem is “You sit in front of a pair of boxes, which are either- both filled with money if Omega predicted you would take one box in this case, otherwise only one is filled”. Note: describing the problem does not require mentioning “Newcomb’s Problem”; it can be expressed as a simple game tree (see here for some explanation of the tree format):
.In comparison, your “Inverse Newcomb” is “Omega gives you some money iff it predicts that you take both boxes in Newcomb’s Problem, an entirely different scenario (ie. not this case).”
The latter is more of the form “Omega arbitrarily rewards agents for taking certain hypothetical actions in a different problem” (of which a nearly limitless variety can be invented to justify any chosen decision theory¹), rather than being an actual self-contained problem which can be “solved”.
The latter also can’t be expressed as any kind of game tree without “cheating” and naming “Newcomb’s Problem” verbally—or rather, you can express a similar thing by embedding the Newcomb game tree and referring to the embedded tree, but that converts it into a legitimate decision problem, which FDT of course gives the correct answer to (TODO: draw an example ;).
(¹): Consider Inverse^2 Newcomb, which I consider the proper symmetric inverse of “Inverse Newcomb”: Omega puts you in front of two boxes and says “this is not Newcomb’s Problem, but I have filled both boxes with money iff I predicted that you take one box in standard Newcomb”. Obviously here FDT takes both boxes and a tidy $1,000,1000 profit (plus the $1,000,000 from Standard Newcomb). Whereas CDT gets… $1000 (plus $1000 from Standard Newcomb).
Yes, you need to have a theory of physics to write down a transition rule for a physical system. That is a problem, but it’s not at all the same problem as the “target format” problem. The only role the transition rule plays here is it allows one to apply induction to efficiently prove some generalization about the system over all time steps.
In principle a different more distinguished concise description of the system’s behaviour could play the a similar role (perhaps, the recording of the states of the system + the shortest program that outputs the recording?). Or perhaps there’s some way of choosing a distinguished “best” formalization of physics. But that’s rather out of scope of what I wanted to suggest here.
But then you are measuring proof shortness relative to that system. And you could be using one of countless other formal systems which always make the same predictions, but relative to which different proofs are short and long.
It would be a O(1) cost to start the proof by translating the axioms into a more convenient format. Much as Kolmogorov complexity is “language dependent” but not asymptotically because any particular universal turing machine can be simulated in any other for a constant cost.
The assumption (including that it takes in and puts out in arabic numerals, and uses “*” as the multuplication command, and that buttons must be pressed,… and all the other things you need to actually use it) includes that.
These are all things that can be derived from a physical description of the calculator (maybe not in fewer steps than it takes to do long multiplication, but certainly in fewer steps than less trivial computations one might do with a calculator). There’s no observer dependency here.
That’s not an issue in my formalization. The “logical facts” I speak of in the formalized version would be fully specified mathematical statements, such as “if the simulation starts in state X at t=0, the state of the simulation at t=T is Y” or “given that Alice starts in state X, then <some formalized way of categorising states according to favourite ice cream flavour> returns
Vanilla”. The “target format” is mathematical proofs. Languages (as in English vs Chinese) don’t and can’t come in to it, because proof systems are language-ignorant.Note, the formalized criterion is broader than the informal “could you do something useful with this simulation IRL” criterion, even though the latter is the ‘inspiration’ for it. For instance, it doesn’t matter whether you understand the programming language the simulation is written in. If someone who did understand the language could write the appropriate proofs, then the proofs exist.
Similarly, if a simulation is run under Homomorphic_encryption, it is nevertheless a valid simulation, despite the fact that you can’t read it if you don’t have the decryption key. Because a proof exists which starts by “magically” writing down the key, proving that it’s the correct decryption key, then proceeding from there.
An informal criterion which maybe captures this better would be: If you and your friend both have (view) access to a genuine computation of some logical facts X, it should be possible to convince your friend of X in fewer words by referring to the alleged computation (but you are permitted unlimited time to think first, so you can reverse engineer the simulation, bruteforce some encryption keys, learn Chinese, whatever you like, before talking). A bit like how it’s more efficient to convince your friend that 637265729567*37265974 = 23748328109134853258 by punching the numbers into a calculator and saying “see?” than by handing over a paper with a complete long multiplication derivation (assuming you are familiar with the calculator and can convince your friend that it calculates correctly).
This idea is, as others have commented, pretty much Dust theory.
The solution, in my opinion, is the same as the answer to Dust theory: namely, it is not actually the case that anything is a simulation of anything. Yes, you can claim that (for instance) the motion of the atoms in a pebble can be interpreted as a simulation of Alice, in the sense that anything can be mapped to anything… but in a certain more real sense, you can’t.
And that sense is this: an actual simulation of Alice running on a computer grants you certain powers—you can step through the simulation, examine what Alice does, and determine certain facts such as Alice’s favourite ice cream flavour (these are logical facts, given the simulation’s initial state). If the simulation is an upload of your friend Alice, then by doing so you learn meaningful new facts about your friend.
In comparison, a pebble “interpreted” as a simulation of Alice affords you no such powers, because the interpretation (mapping from pebble states to simulation data) is entirely post-hoc. The only way to pin down the mapping—such that you could, for instance, explicitly write it down, or take the pebble’s state and map it to an answer about Alice’s favourite ice cream—is to already have carried out the actual simulation, separately, and already know these things about Alice.
In general, “legitimate” computations of certain logical facts (such as the answers one might ask about simulations of people) should, in a certain sense, make it easier to calculate those logical facts then doing so from scratch.
A specific formalization of this idea would be that a proof system equipped with an oracle (axiom schema) describing the states of the physical system which allegedly computed these facts, as well as its transition rule, should be able to find proofs for those logical facts in less steps than one without such axioms.
Such proofs will involve first coming up with a mapping (such as interpreting certain electrical junctions as nand gates), proving them valid using the transition rules, then using induction to jump to “the physical state at timestep t is X therefore Alice’s favourite ice cream colour is Y”. Note that the requirement that these proofs be short naturally results in these “interpretations” being simple.
As far as I know, this specific formalization of the anti-Dust idea is original to me, though the idea that “interpretations” of things as computations ought to be “simple” is not particularly new.
We can (and should) have that discussion, we should just have it on a separate post
Can you point to the specific location that discussion “should” happen at?
As a more powerful version of this, you can install uBlock Origin and configure these custom filters to remove everything on youtube except for the video and the search box. As a user, I don’t miss the comments, social stuff, ‘recommendations’, or any other stuff at all.