[ad510]

Yes, I know that Solomonoff induction is completely impractical for real life machine learning. My point was that if you can survive in the simulation to the point where you see either the 0 or the 1, we don't have any way even in theory (let alone in practice) to guess the probabilities of seeing a 0 or 1, unless you use some sort of learning algorithm. You can use any learning algorithm for this; it doesn't have to be Solomonoff induction.

[jerf]

But your argument seems to fundamentally rest on Solomonoff induction. Put any real algorithm in there, and now you need to ensure that 1. the biases of the algorithm encompass a hypothesis that matches the data and 2. the algorithm will be able to arrive at that hypothesis given a real data stream, and, ideally, a real amount of computation. Both of these are hard questions, in the strongest sense of the term.

And once you open that door, well, all you've really done is restate the fact that learning how the universe works seems to be really difficult.

[ad510]

OK, I see what you're saying now. In that case, can you think of a better way of predicting whether you see a 0 or 1 in that situation?

[jerf]

If I had an answer to that question, I probably wouldn't be putting it on HN. :) I'd be firing it at the market and making boodles of moolah.