But then I realized this understanding of why to use Solomonoff induction is incorrect. We do not use it because of the physical church-turing thesis, we use it because of the original church-turing thesis:
We don’t use it, on the whole.
Because what matters is not whether the universe is computable, but whether our methods of reasoning are computable
Rationalists like Yudkowsky make more extensive claims than the mainstream about SI, specifically that it is a formalised epistemology … in fact a complete formalised ontology, that tells you what reality is, capable of solving long standing philosophical problems, and not restricted to making predictions.
So they think SI actually is revealing the territory. In saying that it is only concerned with the map, you are going back to the relatively modest, mainstream view of SI.
“Solomonoff’s theory of inductive inference is a mathematical proof that if a universe is generated by an algorithm, then observations of that universe, encoded as a dataset, are best predicted by the smallest executable archive of that dataset”
So they think SI actually is revealing the territory. In saying that it is only concerned with the map, you are going back to the relatively modest, mainstream view of SI.
The point of my post is to claim that this view is wrong. The hypotheses in Solomonoff Induction are best thought of as maps, which is a framing that usually isn’t considered (was I the first? 🤔).
If you know of arguments about why considering them to be territories is better, feel free to share them (or links)! (I need a more precise citation than “rationalists” if I’m going to look it up, lol.)
We don’t use it, on the whole.
Rationalists like Yudkowsky make more extensive claims than the mainstream about SI, specifically that it is a formalised epistemology … in fact a complete formalised ontology, that tells you what reality is, capable of solving long standing philosophical problems, and not restricted to making predictions.
So they think SI actually is revealing the territory. In saying that it is only concerned with the map, you are going back to the relatively modest, mainstream view of SI.
“Solomonoff’s theory of inductive inference is a mathematical proof that if a universe is generated by an algorithm, then observations of that universe, encoded as a dataset, are best predicted by the smallest executable archive of that dataset”
The point of my post is to claim that this view is wrong. The hypotheses in Solomonoff Induction are best thought of as maps, which is a framing that usually isn’t considered (was I the first? 🤔).
If you know of arguments about why considering them to be territories is better, feel free to share them (or links)! (I need a more precise citation than “rationalists” if I’m going to look it up, lol.)
I don’t take the view that SI-is-about-the-territory is better … it’s more that what you are saying is locally novel but not globally novel.