HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rundigen12

no profile record

Submissions

Flow Where You Want – Guidance for Flow Models

drscotthawley.github.io
41 points·by rundigen12·7 माह पहले·3 comments

comments

rundigen12
·2 माह पहले·discuss
And why use readable variable names? "aA=q_(c8z,fW8)"

Seriously though, almost all the examples in TFA are of rewriting existing code. It may be that Python is still best for the rapid dev iteration. Then sure, cross-compile into Rust via the LLM.

Plus, If we care about token usage counts, Python has a lot more opportunities for compact "import thing_I_need" than having to generate entire libraries in Rust.
rundigen12
·3 माह पहले·discuss
I honestly expected the demand to be "Release GTA 6 soon or else we will". ...The fact that they're just demanding money is a little disappointing. ;-)
rundigen12
·5 माह पहले·discuss
That was tedious to read. No stable diffusion bugs were ever found. Title is simply wrong. Mod down to spare others.
rundigen12
·7 माह पहले·discuss
An intuitive introduction to adding inference controls to pretrained (latent) flow-based generative models
rundigen12
·9 वर्ष पहले·discuss
I tried some more and still got the "are you sure this is a valid URL?" e.g., https://arxiv.org/abs/gr-qc/0702106

Tried https://arxiv.org/abs/1511.06343 and a couple others and got the "failed to render."

Tried cloning engrafo, then installing docker, then building engrafo, then my disk was filling up and decided I'm done with this for now.
rundigen12
·9 वर्ष पहले·discuss
Tried three papers: "Could not find Arxiv ID in that URL. Are you sure it's an arxiv.org URL?" Why, yes, I copied-and-pasted directly from the browser tab showing the Arxiv URL.

Tried a couple other papers: "This paper failed to render. Take a look at the original PDF instead."

So...with what probability does this actually work?