Shouldn’t the priors be updated and improved each step to be closer to a good prior, and that’s why inaccurate priors may be acceptable? (Do BNNs not iteratively update the (next step’s) prior with the previous step’s posterior?) I haven’t worked on BNNs, but since Bayesian are always talking about updating their priors I thought this would be the case.
Rationality: from AI to Zombies is largely based on Daniel Kahneman’s work, with a bit more influence from Judea Pearl’s causality work. The rationalist subculture has a writing style and trends that might be a bit polarizing, but I found it enjoyable. A good bit of it is about how to quantify uncertainty in real problems, and that this uncertainty only exists in the observer, not the universe. It also considers controversial examples like cryonics, race and politics.