if you don't understand what a discussion is about, the polite thing would be to ask, instead of accusing the participants of showing off.
Humour is risky on the interweb.
It's about this claim:
The core of this claim is that you can apply statistics to learn something about singular events that have never been observed.
interpreted the 3rd and 4th lemmas of the Raven paradox in a Bayesian way which is possible but unnecessary. The original formulation of the paradox doesn't logically imply a Bayesian interpretation. To interpret lemma 3 ("My pet raven is black") and lemma 4 ("This green apple is not black, and it is not a raven") to "strengthen the belief" (FatPhil's words) that "All ravens are black" (lemma 1) is Bayesian thinking in terms of priors strengthening probability. Whereas in first-order logic lemmas 3 and 4 are nothing less and nothing more than statements that are logically consistent
with lemma 1.
From the perspective of scientific reasoning, an observation (of a black raven) can be logically consistent
with a theory while the theory remains false
(all ravens are black). This highlights (1) the multivariate character of the scientific process as compared to straightforward mathematical algorithms and (2) the problem of both (a) naive generalizations and (b) naive applications of Bayesian reasoning which -- when employed in a manner where other relevant variables do not factor in -- statistically strengthens false beliefs.
If you scroll down to Carnap's Bayesian interpretation of the paradox on the linked Wikipedia entry
, he essentially points out that the:
. . . observation of a non-raven does not tell us anything about the color of ravens, but it tells us about the prevalence of ravens, and supports "All ravens are black" by reducing our estimate of the number of ravens that might not be black.
This is due to the ontological assumption that the set of all observable things is far greater than the set of ravens. Carnap's Bayesian interpretation clarifies that the sense in which an observation of a non-raven supports the statement "All ravens are black" is merely by reducing the number of counter-examples ("non-black ravens") amongst the superset of observable things. In other words, if interpreted in a statistical Bayesian way, the paradox is hereby solved and unproblematic.