Cameron Pfiffer

@colehurwitz31 You should be able to extract the log probability from the chain for each sample after you've run it using `chain[:lp]`, with `chain` being the variable containing the value...

AdvancedMH was never intended to support explicit reparameterization, since the whole Turing universe prefers to wrap proposal distributions in bijections. We have a whole package for handling these kinds of...

To be clear, this is not built into AdvancedMH because it is a non-trivial task. A large part of [DynamicPPL.jl](https://github.com/TuringLang/DynamicPPL.jl), Turing's modelling language, is designed to explicitly handle just this...

I'm willing to handle this one, relatively straightforward [to do](https://github.com/ollama/ollama/blob/main/docs/api.md#request-json-mode). As a clarifying question, what's the difference between a regular schema and a managed one?

Oh man, cool! Thanks for starting the issue. I think the vibe of the org is about making it easy and fluid to work with language, text, and other forms...

lmao good bonus -- I wonder if there's something we can do where we have some kind of text on the left or bottom that "explodes" into the Julia colors...

Oh hell yeah I love these as a start. I tend to prefer logos that have a higher center mass, i.e. where the lines/circuits are larger/wider towards the center. But...

Circuit boards might not but this is ART and we can do whatever we want

I think the black background tends to draw a lot of my eye and might make the logo seem a little dark -- I love the standard white Julia logos....

Yeah I actually really love the one with the white background. Any other comments on it?