I can talk about what is in-distribution in terms of a bunch of finite components, and thereby name the cases that are out of distribution: those in which my components break.
(This seems like an advantage inside views have, they come with limits attached, because they build a distribution out of pieces that you can tell are broken when they don’t match reality.)
My example doesn’t talk about the probability I assign on “crazy thing I can’t model”, but such a thing would break something like my model of “who is doing what with the AI code by default”.
Maybe it would have been better of me to include a case for “and reality might invalidate my attempt at meta-reasoning too”?
Idk if it’s actually missing that?
I can talk about what is in-distribution in terms of a bunch of finite components, and thereby name the cases that are out of distribution: those in which my components break.
(This seems like an advantage inside views have, they come with limits attached, because they build a distribution out of pieces that you can tell are broken when they don’t match reality.)
My example doesn’t talk about the probability I assign on “crazy thing I can’t model”, but such a thing would break something like my model of “who is doing what with the AI code by default”.
Maybe it would have been better of me to include a case for “and reality might invalidate my attempt at meta-reasoning too”?
Your comment has made me think I’ve misunderstood something fundamental.
Hm, sorry! I don’t think a good reply on my part should do that :P
I think I’m rejecting a certain mental stance toward unknown-unknowns, and I don’t think I’m clearly pointing at it yet.