Comment by nl

Edit: Here is a Claude artifact you can play with to try this yourself: https://claude.ai/public/artifacts/402f2670-5f48-4d76-96df-8...

You can play with how strong that ("10% per year") prior belief is and see how it affects what the odds are today.

I think the way you are wording this question ("We can test this by going back to 1945 and running forward again?") is an attempt to make it seem "obviously wrong".

Bayesian predictions deal exactly with this type of scenario, where you start with a prior estimate ("Post World War 2, some people had the odds per year at 10%") and then as new information comes along ("It is now 1946. Did we use nuclear weapons again?"... It is now 1956. Did we use nuclear weapons again?") we update our model to try to make the future prediction more accurate.

https://www.stat.berkeley.edu/~aldous/134/lecture4.pdf has example of its use in exactly these kinds of "impossible to rewind" situations. Unfortunately it doesn't have the worked solutions.

https://math.mit.edu/~dav/05.dir/class11-prep.pdf is pretty good because it shows how updating the model with new data changes the odds.