regular impression is a user on octodon.social. You can follow them or interact with them if you have an account anywhere in the fediverse.
If you don't, you can sign up here.
Found myself wondering about an interesting philosophical problem with some of the assumptions of machine learning, which led me to an interesting philosophy stackexchange thread: https://philosophy.stackexchange.com/questions/40581/on-wittgensteins-family-resemblance-and-machine-learning
My line of thought is that a Russellian theory of meaning is kind of baked into the idea of a classification problem, and that class membership of real world things doesn't always behave as discretely as Russell would have liked.