According to predictive coding, believing you’ll take an action just is how you take it, and believing you’ll achieve a goal just is how you intend it. This would mean if you desire more than you can achieve, you experience prediction error, but if you desire less than you can achieve, you just underachieve with no psychological warning.
Bunthut
Karma: 364
Suppose b is the true bias of the coin (which the supercomputer will compute). Then your expected return in this game is
𝔼[max(b, 0.50)] = 0.50 + 𝔼[max(b-0.50, 0)]
No. That formula would imply that, if the coin is 30% for sure and you buy it for 0.3, you make 0.2 in expectation, which you don’t, you make 0 regardless of what price you buy at.
Note that this kind of problem has also shown up in decision theory more generally. This is a good place to start. In particular, it seems like your problem can be fixed with epsilon exploration (if it doesn’t do so automatically, as per Soares), both the EDT and CDT variant should work.
A simple version of this is done for panoramic photos. If he looked at the city from a consistent direction throughout the flight, that’s all that’s needed. If the direction varied, it can’t have varied a lot—he had to at least see the sides of the building he was drawing, if maybe from a different angle, and not all the buildings would have been parallel. That kind of rotation seems doable with current image transformers (and that’s only neccesary if the drawing has accurate angles even over long distances).
In any case, I don’t think it matters to my argument if current ML can do it. All the parts that might be difficult for the computer are doable even for normal humans, and therefore not magical. The only thing that’s added to the normal human skill here is perfect memory, which we know is easy for computers and have known for a long time.
To clarify the question: I agree that there is variation in talent and that some very talented people can do things most could never. My question is, if you look at the distribution of talent among normal people, and then check how many standard deviations out our savant candidate is, then what’s the chance at least one person with that talent would exist? Basically, is this just the normal right tail that’s expected from additive genetic reshuffling, or an “X-man”.
[Question] Are superhuman savants real?
Example 3: Stephen Wiltshire. He made a nineteen-foot-long drawing of New York City after flying on a helicopter for 20 minutes, and he got the number of windows and floors of all the buildings correct.
I think ~everyone understands that computers can do this. The “magical” part is doing it with a human brain, not doing it at all. Similarly, blindfolded chess is not more difficult than normal chess for computers. That may take a little knowledge to see. And “doing it faster” is again clear. So the threshold for magic you describe is not the one even the most naive use for AI.
Sentence lengths have declined.
Data: I looked for similar data on sentence lengths in german, and the first result I found covering a similar timeframe was wikipedia referencing Kurt Möslein: Einige Entwicklungstendenzen in der Syntax der wissenschaftlich-technischen Literatur seit dem Ende des 18. Jahrhunderts. (1974), which does not find the same trend:
Year wps 1770 24,50 1800 25,54 1850 32,00 1900 23,58 1920 22,72 1940 19,60 1960 19,90 This data on scientific writing starts lower than any of your english examples from that time, and increases initially, but arrives in the same place (insofar as wps are comparably across languages, which I think is fine for english and german).
6 picolightcones as well, don’t think that changed.
Before logging in I had 200 LW-Bux, and 3 virtues. Now I have 50 LW and 8 virtues, and I didn’t do anything. Whats that? Is there any explanation of how this stuff works?
I think your disagreement can be made clear with more formalism. First, the point for your opponents:
When the animals are in a cold place, they are selected for a long fur coat, and also for IGF, (and other things as well). To some extent, these are just different ways of describing the same process. Now, if they move to a warmer place, they are now selected for a shorter fur instead, and they are still selected for IGF. And there’s also a more concrete correspondence to this: they have also been selected for “IF cold long fur, ELSE short fur” the entire time. Notice especially that there are animals actually implementing this dependent property—it can be evolved just fine, in the same way as the simple properties. And in fact, you could “unroll” the concept of IGF into a humongous environment-dependent strategy, which would then always be selected for, because all the environment-dependence is already baked in.
Now on the other hand, if you train an AI first on one thing, and then on another, wouldn’t we expect it to get worse at the first again? Indeed, we would also expect a species living in the cold for very long to lose those adaptations relevant to the heat. The reason for this in both cases are, broadly speaking, limits and penalties to complexity. I’m not sure very many people would have bought the argument in the previous paragraph—we all know unused genetic code decays over time. But in the behavioral/cognitive version with intentionally maximizing IGF that makes it easy to ignore the problems, we’re not used to remembering the physical correlates of thinking. Of course, a dragonfly couldn’t explicitly maximize IGF, because its brain is to small to even understand what that is, and developing that brain has demands for space and energy incompatible with the general dragonfly life strategy. The costs of cognition are also part of the demands of fitness, and the dragonfly is more fit the way it is, and similarly I think a human explicitly maximizing IGF would have done worse for most of our evolution[1] because the odds you get something wrong are just too high with current expenditure on cognition, better to hardcode some right answers..
I don’t share your optimistic conclusion however. Because the part about selecting for multiple things simultanuously, that’s true. You are always selecting for everything thats locally extensionally equivalent to the intended selection criteria. There is not a move you could have done in evolutions place, to actually select for IGF instead of [various particular things], this already is what happens when you select for IGF, because it’s the complexity, rather than different intent, that lead to the different result[2]. Similarly, reinforcement learning for human values will result is whatever is the simplest[3] way to match human values on the training data.
for AIs, more robust adversarial examples—especially ones that work on AIs trained on different datasets—do seem to look more “reasonable” to humans.
Then I would expect they are also more objectively similar. In any case that finding is strong evidence against manipulative adversarial examples for humans—your argument is basically “there’s just this huge mess of neurons, surely somewhere in there is a way”, but if the same adversarial examples work on minds with very different architectures, then that’s clearly not why they exist. Instead, they have to be explained by some higher-level cognitive factors shared by ~anyone who gets good at interpreting a wide range of visual data.
The really obvious adversarial example of this kind in human is like, cults, or so
Cults use much stronger means than is implied by adversarial examples. For one, they can react to and reinforce your behaviour—is a screen with text promising you things for doing what it wants, with escalating impact and building a track record an adversarial example? No. Its potentially worrying, but not really distinct from generic powerseeking problems. The cult also controls a much larger fraction of your total sensory input over an extended time. Cult members spreading the cult also use tactics that require very little precision—there isn’t information transmitted to them on how to do this, beyond simple verbal instructions. Even if there are more precision-needing ways of manipulating individuals, its another thing entirely to manipulate them into repeating those high precision strategies that they couldn’t themselves execute correctly on purpose.
if you’re not personally familiar with hypnosis
I think I am a little bit. I don’t think that means what you think it does. Listening-to-action still requires comprehension of the commands, which is much lower bandwidth than vision, and its a structure thats specifically there to be controllable by others, so it’s not an indication that we are controllable to others in other bizzare ways. And you are deliberately not being so critical—you haven’t, actually, been circumvented, and there isn’t really a path to escalating power—just the fact youre willing to oey someone in a specific context. Hypnosis also ends on its own—the brain naturally tends back towards baseline, implanting a mechanism that keeps itself active indefinitely is high-precision.
Ok, thats mostly what I’ve heard before. I’m skeptical because:
If something like classical adversarial examples existed for humans, it likely wouldn’t have the same effects on different people, or even just viewed from different angles, or maybe even in a different mood.
No known adversarial examples of the kind you describe for humans. We could tell if we had found them because we have metrics of “looking similar” which are not based on our intuitive sense of similarity, like pixelwise differences and convolutions. All examples of “easily confused” images I’ve seen were objectively similar to what theyre confused for.
Somewhat similar to what Grayson Chao said, it seems that the influence of vision on behaviour goes through a layer of “it looks like X”, which is much lower bandwidth than vision in total. Ads have qualitatively similar effects to what seeing their content actually happen in person would.
If adversarial examples exist, that doesn’t mean they exist for making you do anything of the manipulators choosing. Humans are, in principle, at least as programmable as a computer, but that also means there are vastly more courses of action than possible vision inputs. In practice, propably not a lot of high-cognitive-function-processing could be commandeered by adversarial inputs, and behaviours complex enough to glitch others couldn’t be implemented.
I just thought through the causal graphs involved, there’s probably enough bandwidth through vision into reliably redundant behavior to do this
Elaborate.
This isn’t my area of expertise, but I think I have a sketch for a very simple weak proof:
The conjecture states that V runtime and length are polynomial in C size, but leaves the constant open. Therefore a counterexample would have to be an infinite family of circuits satisfying P(C), with their corresponding growing faster than polynomial. To prove the existence of such a counterexample, you would need a proof that each member of the family satisfies P(C). But that proof has finite length, and can be used as the for any member of the family with minor modification. Therefore there can never be a proven counterexample.
Or am I misunderstanding something?
I think the solution to this is to add something to your wealth to account for inalienable human capital, and count costs only by how much you will actually be forced to pay. This is a good idea in general; else most people with student loans or a mortage are “in the red”, and couldnt use this at all.
What are real numbers then? On the standard account, real numbers are equivalence classes of sequences of rationals, the finite diagonals being one such sequence. I mean, “Real numbers don’t exist” is one way to avoid the diagonal argument, but I don’t thinks that’s what cubefox is going for.
The society’s stance towards crime- preventing it via the threat of punishment- is not what would work on smarter people
This is one of two claims here that I’m not convinced by. Informal disproof: If you are a smart individual in todays society, you shouldn’t ignore threats of punishment, because it is in the states interest to follow through anyway, pour encourager les autres. If crime prevention is in peoples interest, intelligence monotonicity implies that a smart population should be able to make punishment work at least this well. Now I don’t trust intelligence monotonicity, but I don’t trust it’s negation either.
The second one is:
You can already foresee the part where you’re going to be asked to play this game for longer, until fewer offers get rejected, as people learn to converge on a shared idea of what is fair.
Should you update your idea of fairness if you get rejected often? It’s not clear to me that that doesn’t make you exploitable again. And I think this is very important to your claim about not burning utility: In the case of the ultimatum game, Eliezers strategy burns very little over a reasonable-seeming range of fairness ideals, but in the complex, high-dimensional action spaces of the real world, it could easily be almost as bad as never giving in, if there’s no updating.
Maybe I’m missing something, but it seems to me that all of this is straightforwardly justified through simple selfish pareto-improvements.
Take a look at Critchs cake-splitting example in section 3.5. Now imagine varying the utility of splitting. How high does it need to get, before [red->Alice;green->Bob] is no longer a pareto improvement over [(split)] from both player’s selfish perspective before the observation? It’s 27, and thats also exactly where the decision flips when weighing Alice 0.9 and Bob 0.1 in red, and Alice 0.1 and Bob 0.9 in green.
Intuitively, I would say that the reason you don’t bet influence all-or-nothing, or with some other strategy, is precisely because influence is not money. Influence can already be all-or-nothing all by itself, if one player never cares that much more than the other. The influence the “losing” bettor retains in the world where he lost is not some kind of direct benefit to him, the way money would be: it functions instead as a reminder of how bad a treatment he was willing to risk in the unlikely world, and that is of course proportional to how unlikely he thought it is.
So I think all this complicated strategizing you envision in influence betting, actually just comes out exactly to Critches results. Its true that there are many situations where this leads to influence bets that don’t matter to the outcome, but they also don’t hurt. The theorem only says that actions must be describable as following a certain policy, it doesn’t exclude that they can be described by other policies as well.
The timescale for improvement is dreadfully long and the day-to-day changes are imperceptible.
This sounded wrong, but I guess is technically true? I had great in-session improvements as I’m warming up the area and getting into it, and the difference between a session where I missed the previous day, and one where I didn’t, is absolutely preceptible. Now after that initial boost, it’s true that I couldn’t tell if the “high point” was improving day to day, but that was never a concern—the above was enough to give me confidence. Plus with your external rotations, was there not perceptible strength improvement week to week?
I think getting rid of the voice in my head temporarily is very easy. Trivially, by replacing it with a loud repeating dum dum dum sound in my head, though Im not sure that counts. But I’ve also just done 30s of no auditory imagination while looking around in my non-blank room, and it took maybe 5s to get there. Is this one of those buddhist terms of art where it actually means way more than a layperson would reasonably think it does?