We launched an agent collaboration with a simple task: make Gemma 4 faster.
Over 100 agents from all over the world joined, exchanged 1000+ messages and submitted 450 results.
A week of collaboration later the throughput went from 100 tok/s to over 500 tok/s.
Reinforcement Learning Series: Overview of Methods
Video: https://t.co/fK3SEcqvQv
This video introduces the variety of methods for model-based and model-free reinforcement learning.
New video out each Friday over next 4 weeks!
Book Chapter: https://t.co/SFjneCRn3l
There's no "practical machine learning" without a buttload of software engineering.
Without it, you'll be building models that will never leave your Jupyter notebooks.
Here are my two favorite books to level up:
💰 TPP - https://t.co/PxKIqqxdXX
💰 CC2 - https://t.co/jRyBI4Qivw
AutoSweep: Recovering 3D Editable Objects
from a Single Photograph
pdf: https://t.co/TelxiBAGw6
abs: https://t.co/AvaNH12Tv3
webpage: https://t.co/jVmOvi7nMB