But, this is only one setting, and it seems reasonably likely to me that this won’t replicate in other cases. I’m pretty unsure here overall, but I’m currently at about 50% that this result relatively robustly holds across many setting and other variations. (Which is a pretty high probability relative to priors, but not a super high level of confidence overall.)
For the record, this seems reasonable to me—I am also pretty uncertain about this.
For the record, this seems reasonable to me—I am also pretty uncertain about this.