The case against assigning probabilities to existential risk
It’s announcement time! And no, the announcement is not that I accidentally wrote the same word twice. It’s that I’ll be kicking of a few series of posts cal...
A common issue with predictions from models is that you’ve trained in a dataset where the base rate (or prevalence) is different to that in your target data...
I think the title says the stuff I came here to say. Yay! A lot of hard work, a viva, (minor) corrections and it’s finally online and out there.
What I do now I waste a lot of time rewriting boilerplate in matplotlib. I don’t think that’s a particularly bad thing as it helps me remember all the basics...