I think his point is that you are still entirely unable to even enumerate, let alone process, all the relevant hypotheses, nor does the formula inform you of those, nor does it inform you how to deal with cyclic updates (or even that those are a complicated case), etc. It's particularly bad when it comes to what rationalists describe as "expected utility calculations". The ideal expected utility is a sum of the differential effect of the actions being compared, over all hypotheses, multiplied with their probabilities... a single component of the sum provides very little or no information about the value of the sum, especially when picked by someone with a financial interest as strong as "if i don't convince those people I can't pay my rent". Then, the actions themselves have an impact on the future decision making, which makes the expected value sum grow and branch out like some crazy googol-headed fractal hydra. Mostly when someone's talking much about Bayes they have some simple and invalid expected value calculation that they want you to perform and act upon, so that you'll be worse off in the end and they'll be better off in the end.

Could we start that reading with the classic Bayes' Theorem example? Suppose 1% of women have breast cancer, 80% of mammograms on a cancerous woman will detect it, 9.6% on an uncancerous woman will be false positives. Suppose woman A gets a mammogram which indicates cancer. What are the odds she has cancer? p(A|X) = p(X|A)p(A)/(p(X|A)p(A)+p(X|~A)p(~A)) = 7.8% Hooray? Now suppose women B, C, D, E, F... Z, AA, AB, AC, AD, etc., the entire patient list getting screened today, all test positive for cancer. Is the probability that woman A has cancer still 7.8%? Bayes' rule, with the priors above, still says "yes"! You need more complicated prior probabilities (e.g. what are the odds that the test equipment is malfunctioning?) before your evidence can tell you what's actually likely to be happening. But those more complicated, more accurate priors would have (very slightly) changed our original p(A|X) as well! It's not that Bayesian updating is wrong. It's just that Bayes' theorem never allows you to have a non-zero posterior probability coming from a zero prior, and to make any practical problem tractable everybody ends up implicitly assuming huge swaths of zero prior probability.