A collection of notes, usually ML concepts, implementations and papers that I have been reading about recently. Longer then tweets..

Posts

Why Do Multi-Agent LLM Systems Fail?

MAST (Multi-Agent System Failure Taxonomy)
Read More
#Agent #Improvement #Failure

Self Improvement

A comprehensive look at how AI systems are learning to improve themselves
Read More
#Agent #Improvement

Deepseek's Janus Models

Multimodal understanding and generation from the same models.
Read More
#Multimodal #Janus #Deepseek

Modern BERT

A Much-Needed Update to an ML Workhorse
Read More
#NLP #BERT #Transfer-Learning

Gemma Scope

Open Sparse Autoencoders Everywhere All At Once on Gemma 2
Read More
#Tutorial #Gemma #SAE #Sparse #Interpretability