Stories by research_pie

How to stop feeling lost in tech: the wafflehouse method

Muon Optimizer Explained to a Toddler

Next Frontier for LLM Is Quality Long Context

What is the Transformers' Context Window? (and how to make it LONG)

What Are Multi-Agent Systems? – Monte-Carlo Search Tree and Role Playing

How Minimax-01 Achieves 1M Token Context Length with Linear Attention (MIT)

Tiled Matrix Multiplication (2019)

You shouldn't build autonomous agent

AI Engineering Is Stochastic Software Development

Group Relative Policy Optimization (GRPO)

DeepSeek R1 Theory Overview (GRPO and RL and SFT)

How to Master Deep Learning Math?

How to Do Scientific Research in Undergrad?

How to Read Deep Learning Code?

Interesting Deep Learning Research Pattern [video]

QHAdam Optimizer Explained – Theory and Code

How to Read Math in Deep Learning Paper?

Numerical Stability with Log Softmax Explained

How to Read Deep Learning Paper as a Software Engineer

1