AI/ML
Hypothesis generation and Maximum Likelihood Estimation
The guiding principle to follow for building models
Hi, I'm Manav Dahra
Backend Engineer & AI Interpretability Enthusiast
Exploring the depths of software engineering and AI safety through mechanistic interpretability. Sharing insights from a decade of building distributed systems and recent deep dives into understanding how AI models really work.
Latest Posts
AI/ML
Intro to Machine learning
The right way to approach ML and why it is important to learn the Math
Interactive Demo
3D Snake Game: WebGL Physics Demo
A playable 3D snake game built with Three.js and Cannon.js physics engine. Use arrow keys or touch controls to play!
What I Write About
Software Engineering
Distributed systems, microservices architecture, databases, and building scalable applications that serve millions of users.
AI Interpretability
Mechanistic interpretability, transformer circuits, AI safety research, and understanding what happens inside neural networks.
System Design
Real-world architectural patterns, performance optimization, and lessons learned from building production systems.
Deep Learning
PyTorch, transformers, reinforcement learning, and practical applications of machine learning in production.