Setting up your code environment is often the 1st step when building LLMs for education, research, or production. Made a new video where share my personal setup: "Build an LLM from Scratch 1: Set up your code environment": https://
youtube.com/watch?v=yAcWnf
sZhzo
…
(Are videos like this helpful?)
@rasbt
-
Building LLMs from Scratch: Setting Up Your Code Environment
By
–
-
Gemini as an Introductory Code Assistant Tool for Beginners
By
–
Btw I am not saying this is a good tool or I recommend it (I haven't actually even used Gemini really). My main read of this was that it's a nice intro code assistant for more people to try out and learn how to integrate code assistants into their workflow.
-
Mixed Feedback on VSCode Integration, Curious to Try
By
–
Just seeing the feedback on the VSCode integration is also mixed. But I am curious and will probably give it a try anyways this week.
-
Gemini Code Assist vs Claude 3.7: Different Use Cases in Development
By
–
I think it is a slightly different use case in a typical workflow. I think Gemini Code Assist is more meant as your always-on Copilot-style VSCode plugin. Claude 3.7 is sth you explicitly ask to generate specific code, provide code feedback etc. Pls correct me if I'm wrong.
-
Google releases free Gemini Code Assist and code review agent
By
–
Just heard that Gemini Code Assist, Google's alternative to GitHub Copilot, is now free, which is fantastic news. Additionally, Google released a free GitHub code review agent! This is great, because it lowers the barrier to entry to try and incorporate these tools into our
-
Hugging Face R1 reproduction pipeline adopts uv tool
By
–
Was just trying out the @huggingface R1 reproduction pipeline and saw they are recommending and using uv now too https://
github.com/huggingface/op
en-r1
… -
Claude Version Naming Improvements Discussion
By
–
Not sure if 'Claude 3.5 Sonnet & new Claude 3.5 Sonnet' was that much better than 'o1-preview and o1' in terms of version naming. But yeah, glad they fixed that with 3.7
-
Parallel Best-of-N Sampling and Majority Voting for LLM Improvement
By
–
Sure! The simplest example would be parallel Best-of-N sampling and using majority vote or a verifier. Google had a good paper on that last summer: https://
arxiv.org/abs/2408.03314 -
Multi-head Latent Attention Innovation and OpenAI’s Mixture-of-Experts
By
–
Good point. They brought us multi-head latent attention last summer.
(I'm not counting mixture-of-experts, because OpenAI uses it regardless of constraints :P) -
Apple Intelligence Implementation Based on Official Paper
By
–
Yes, Apple Intelligence uses it if we can believe Apple's paper (
https://
arxiv.org/abs/2407.21075):