You discussed this over here too, with greater hostility:
also someone somehow thinks that Solomonoff induction finds probabilities for theories, while it just assigns 2^-length as probability for software code of such length, which is obviously absurd when applied to anything but brute force generated shortest pieces of code,
I’m trying to figure out whether, when you say “someone”, you mean someone upthread or one of the original authors of the post. Because if it’s the post authors, then I get to accuse you of not caring enough about refraining from heaping abuse on writers who don’t deserve it to actually bother to check whether they made the mistake you mocked them for. The post includes discussion of ideals vs. approximations in the recipe metaphor and in the paragraph starting “The actual process above might seem a little underwhelming...”:
We just check every single hypothesis? Really? Isn’t that a little mindless and inefficient? This will certainly not be how the first true AI operates. But don’t forget that before this, nobody had any idea how to do ideal induction, even in principle. Developing fundamental theories, like quantum mechanics, might seem abstract and wasteful. [...] such theories and models change the world, as quantum mechanics did with modern electronics. In the future, [...] ways to approximate Solomonoff induction [...] Perhaps they will develop methods to eliminate large numbers of hypotheses all at once. Maybe hypotheses will be broken into distinct classes. Or maybe they’ll use methods to statistically converge toward the right hypotheses.
Everyone knows there are practical difficulties. Some people expect that someone will almost certainly find a way to mitigate them. You tend to treat people as idiots for going ahead with the version of the discussion that presumes that.
With respect to your objections about undiscoverable short programs, presumably people would look for ways to calibrate the relationship between the description lengths of the theories their procedures do discover (or the lengths of the parts of those theories) and the typical probabilities of observations, perhaps using toy domains where everything is computable and Solomonoff probabilities can be computed exactly. Of course, by diagonalization there are limits to the power of any finite such procedure, but it’s possible to do better than assuming that the only programs are the ones you can find explicitly. Do you mean to make an implicit claim by your mockery which special-cases to the proposition that what makes the post authors deserve to be mocked is that they didn’t point out ways one might reasonably hope to get around this problem, specifically? (Or, alternatively, is the cause of your engaging in mockery something other than a motivation to express propositions (implicit or explicit) that readers might be benefited by believing? For example, is it a carelessly executed side-effect of a drive to hold your own thinking to high standards, and so to avoid looking for ways to make excuses for intellectual constructs you might be biased in favor of?)
It is the case that Luke, for instance of an author of this post, wrote this relatively recently. While there is understanding that bruteforcing is the ideal, I do not see understanding of how important of a requirement that is. We don’t know how long is the shortest physics, and we do not know how long is the shortest god-did-it, but if we can build godlike AI inside our universe then the simplest god is at most same length and unfortunately you can’t know there isn’t a shorter one. Note: I am an atheist, before you jump onto he must be theist if he dislikes that statement. Nonetheless I do not welcome pseudo-scientific justifications of atheism.
edit: also by the way, if we find a way to exploit quantum mechanics to make a halting oracle and do true Solomonoff induction some day, that would make physics of our universe incomputable and this amazing physics itself would not be representable as Turing machine tape, i.e. would be a truth that Solomonoff induction we could do using this undiscovered physics would not be able to even express as a hypothesis. Before you go onto Solomonoff induction you need to understand Halting problem and variations, otherwise you’ll be assuming that someday we’ll overcome Halting problem, which is kind of fine except if we do then we just get ourselves the Halting problem of the second order plus a physics where Solomonoff induction doable with the oracle does not do everything.
You discussed this over here too, with greater hostility:
I’m trying to figure out whether, when you say “someone”, you mean someone upthread or one of the original authors of the post. Because if it’s the post authors, then I get to accuse you of not caring enough about refraining from heaping abuse on writers who don’t deserve it to actually bother to check whether they made the mistake you mocked them for. The post includes discussion of ideals vs. approximations in the recipe metaphor and in the paragraph starting “The actual process above might seem a little underwhelming...”:
Everyone knows there are practical difficulties. Some people expect that someone will almost certainly find a way to mitigate them. You tend to treat people as idiots for going ahead with the version of the discussion that presumes that.
With respect to your objections about undiscoverable short programs, presumably people would look for ways to calibrate the relationship between the description lengths of the theories their procedures do discover (or the lengths of the parts of those theories) and the typical probabilities of observations, perhaps using toy domains where everything is computable and Solomonoff probabilities can be computed exactly. Of course, by diagonalization there are limits to the power of any finite such procedure, but it’s possible to do better than assuming that the only programs are the ones you can find explicitly. Do you mean to make an implicit claim by your mockery which special-cases to the proposition that what makes the post authors deserve to be mocked is that they didn’t point out ways one might reasonably hope to get around this problem, specifically? (Or, alternatively, is the cause of your engaging in mockery something other than a motivation to express propositions (implicit or explicit) that readers might be benefited by believing? For example, is it a carelessly executed side-effect of a drive to hold your own thinking to high standards, and so to avoid looking for ways to make excuses for intellectual constructs you might be biased in favor of?)
It is the case that Luke, for instance of an author of this post, wrote this relatively recently. While there is understanding that bruteforcing is the ideal, I do not see understanding of how important of a requirement that is. We don’t know how long is the shortest physics, and we do not know how long is the shortest god-did-it, but if we can build godlike AI inside our universe then the simplest god is at most same length and unfortunately you can’t know there isn’t a shorter one. Note: I am an atheist, before you jump onto he must be theist if he dislikes that statement. Nonetheless I do not welcome pseudo-scientific justifications of atheism.
edit: also by the way, if we find a way to exploit quantum mechanics to make a halting oracle and do true Solomonoff induction some day, that would make physics of our universe incomputable and this amazing physics itself would not be representable as Turing machine tape, i.e. would be a truth that Solomonoff induction we could do using this undiscovered physics would not be able to even express as a hypothesis. Before you go onto Solomonoff induction you need to understand Halting problem and variations, otherwise you’ll be assuming that someday we’ll overcome Halting problem, which is kind of fine except if we do then we just get ourselves the Halting problem of the second order plus a physics where Solomonoff induction doable with the oracle does not do everything.