Axel Hedman (@knappen_h) 's Twitter Profile
Axel Hedman

@knappen_h

a.k.a Knappen

ID: 4392961576

calendar_today06-12-2015 10:24:26

1 Tweet

38 Followers

154 Following

Google Research (@googleresearch) 's Twitter Profile Photo

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: goo.gle/47LJrzI

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: goo.gle/47LJrzI
Towards Data Science (@tdatascience) 's Twitter Profile Photo

Understand the limits of vibe-coding. This article covers where AI-driven coding is useful for prototypes and where it falls short for production-grade systems that require accountability. By Elisha Rosensweig and Eitan Wagner towardsdatascience.com/human-wont-rep…

Towards Data Science (@tdatascience) 's Twitter Profile Photo

Partha Sarkar shares practical insights on GraphRAG, discussing design principles, limitations, and best practices for building scalable retrieval systems. towardsdatascience.com/do-you-really-…

Jeff Dean (@jeffdean) 's Twitter Profile Photo

We have a long history of model architecture innovations, and we're continuing to explore new ideas. Here's some early work that shows promising results on extending the context length over which a model can reason over.

Lisan al Gaib (@scaling01) 's Twitter Profile Photo

> random youtube guy > begins 2 hour video with "today i'm bored" > continues to create ML library from scratch in C > types everything manually at 150 wpm in neovim > trains mnist classification model with his library > "that is pretty cool" > chuckles > leaves just imagine

> random youtube guy
> begins 2 hour video with "today i'm bored"
> continues to create ML library from scratch in C
> types everything manually at 150 wpm in neovim
> trains mnist classification model with his library
> "that is pretty cool"
> chuckles
> leaves

just imagine