mxs_ · HackerTrans

vor 5 Monatendiscuss

they have really tried hard to make the entire OS less usable. I'm not an "iToddler", I paid for a Unix workstation and will not have lower information density forced onto me.

mxs_

vor 5 Monatendiscuss

I there a way to make this work with macOS hosts, preferably without having to install a Linux toolchain inside the VM for the language the agent will be writing code in?

mxs_

vor 10 Monatendiscuss

Remote dev isn't very good in Zed, unfortunately. For some reason they chose not to apply the local editor's settings to a remote session by default. Every remote has its own config file. Questionable choice, imo

mxs_

letztes Jahrdiscuss

In their tech report, they say this is based on:

> "Our methods extend [28] through careful modifications to the data and computation to scale up learning."

[28] is Lou et al. (2023), the "Score Entropy Discrete Diffusion" (SEDD) model (https://arxiv.org/abs/2310.16834).

I wrote the first (as far as I can tell) independent from-scratch reimplementation of SEDD:

https://github.com/mstarodub/dllm

My goal was making it as clean and readable as possible. I also implemented the more complex denoising strategy they described (but didn't implement).

It runs on a single GPU in a few hours on a toy dataset.

mxs_

vor 2 Jahrendiscuss

obligatory: https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQyItWM...

comments