// Blog
Exploring AI/ML — neural networks, transformers, LLMs, and everything in between.
A beginner-friendly guide to neural networks — how they work, why they matter, and how to build one from scratch in PyTorch.
Understanding the transformer architecture that powers GPT, BERT, and every modern LLM.
Everything you need to know about tensors — what they are, how they work, and why they're the backbone of ML.
Get started with PyTorch — tensors, autograd, building models, and training your first neural network.
How RAG combines the power of retrieval systems with LLMs to give accurate, up-to-date answers.
How to fine-tune large language models for your specific use case without breaking the bank.
Understanding the training technique behind DeepSeek R1 — where RL meets verifiable correctness.
How to build complex, stateful AI applications using LangGraph's graph-based approach.
A deep dive into how LLMs are trained, how they generate text, and what makes them tick.
