From foundational Deep Learning training techniques to the algorithms powering modern Agentic AI.As you probably already know, Artificial Intelligence is becoming the new Internet, or the new electricity, as many people are saying. And of course, the f…
Picture walking into your own room after a long day, where a companion not only knows your name but remembers you mentioned feeling overwhelmed just last week. It detects your frown, softens its tone in empathy, and leans in to listen. This is the real…
How I used Ollama, Python, and a simple Chrome Extension to figure out if an article is worth my time.Continue reading on Towards AI »
The open source project Jensen Huang called the next ChatGPT, what it actually does, how it works under the hood, and why every company is suddenly asking the same question.Last week at Nvidia GTC 2026, Jensen Huang walked onstage and said something th…
Series: An Engineer’s Explorations in LLM Concepts“It started with a simple question: What exactly is a token? Three hours later, I had filled six browser tabs, youtube videos and had somehow ended up reading about some 5–6 concepts of LLM.”If you’ve w…
Moving Beyond Manual Prompting: A Practical Introduction to DSPyHave you ever spent hours crafting the perfect prompt, only to have it break when you switch LLM models? Or have you watched your carefully engineered prompts not work as expected when you…
A simple breakdown of LatentMoE, 1M context, reinforcement learning, and NVIDIA’s open model strategyContinue reading on Towards AI »
When I first read about BERT (Bidirectional Encoder Representations from Transformers), the number one question that plagued my mind was a simple definition issue.We are told BERT is “Bidirectional.” But wait — BERT is based on the Transformer Encoder….
Eleven retrieval strategies — from a 1972 term counter to hypothetical hallucinations — and why the one you pick silently determines…Continue reading on Towards AI »
Why My RAG System Struggled with the Bible — and How I Fixed ItIntroductionI was building a Retrieval-Augmented Generation (RAG) system for a Bible question-answering application when I ran into a surprising problem. The system worked well for direct v…