David Manheim on Bayesian analysis is the right framewor…

David Manheim

Researcher and LessWrong commenter on probabilistic reasoning and risk

I think most points here are good points to make, but I also think it's useful as a general caution against this type of exercise being used as an argument at all! So I'd obviously caution against anyone taking your response itself as a reasonable attempt at an estimate of the "correct" Bayes factors, because this is all very bad epistemic practice!

AI Verified source (Feb 19, 2024)

3mo ago

Policy proposals and claims

Bayesian analysis is the right framework for settling the COVID-19 origins question

votes Against

Statement relation verification history AI Verified Report this

AI Verified The quote is directly about the source’s use of Bayesian/Bayes-factor reasoning on COVID-19 origins, and in context the commenter says that kind of argument is "very bad epistemic practice" and even "fundamentally flawed" when used as an argument, which makes a non-supportive stance on the statement substantially more likely. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

AI Verified Relevant: on the source page, "this type of exercise" refers to using informal Bayes-factor/Bayesian reasoning about COVID origins, and the author says it is "bad epistemic practice" and "fundamentally flawed" when used as an argument. That is directly about the statement and gives a determinable stance signal. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

Vote inference verification history Latest opinion AI Verified Report this

AI Verified He opposes using this kind of Bayesian/Bayes-factor reasoning to resolve the issue: he warns against the exercise being used "as an argument at all," calls it "very bad epistemic practice," and says that in this case it is being presented as an argument, which "is not how any of this should work." That supports "against" for Bayesian analysis as the right framework for settling COVID origins, even though he allows a narrow private use for self-updating. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

AI Verified He is criticizing Bayesian/Bayes-factor analysis as a way to settle this question in the form presented: he warns against “this type of exercise being used as an argument at all,” says it should not be taken as an estimate of the “correct” Bayes factors, calls it “very bad epistemic practice,” and adds that presented publicly “as an argument ... is not how any of this should work.” That makes opposition to the statement more likely, even though his target is especially this informal/public use rather than Bayesian reasoning in every sense. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

Quote authenticity verification history

Report this

AI Verified The LessWrong source URL contains this passage in a comment by the user Davidmanheim, and the quoted sentence matches verbatim up to the final exclamation point. A GreaterWrong mirror gives the comment’s timestamp as 19 Feb 2024 13:53 UTC. External publications by David Manheim use the same davidmanheim identifier/email, so the attribution is consistent. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

AI Verified The quote is authentic. It appears verbatim on the cited LessWrong page in a comment attributed to Davidmanheim, beginning “Thank you for writing this” and continuing through “because this is all very bad epistemic practice!” The GreaterWrong mirror of the same thread shows that comment with the exact timestamp 19 Feb 2024 13:53 UTC, which matches the stored day-level date of Feb 19, 2024. I found no reliable evidence requiring changes to the stored quote text, author, date, or source URL. ([lesswrong.com](https://www.lesswrong.com/posts/NrKQGyggC7jcersuJ/on-coincidences-and-bayesian-reasoning-as-applied-to-the)) · YouCongress gpt-5.4-2026-03-05 · 3mo ago

replying to David Manheim

Other opinions from David Manheim

See all

David Manheim votes Against

Bayesian analysis is the right framework for settling the COVID-19 origins question

That is, this type of informal Bayesian estimate is useful as part of a ritual for changing your own mind, when done carefully. That requires a significant degree of self-composure, a willingness to change one's mind, and a high degree of justified c...

more AI Verified source (Feb 19, 2024)