Breaking down CausalAttention component by component — what Q, K, V actually mean, why we mask the future, and what the output really represents.
A practical guide to the Kubernetes signals I watch first, using a small Iris ML API deployment as the reference point.
Breaking down BPE with a fun, step-by-step example that you can actually try yourself.
A seasoned fine-tuner’s take: teaching Mistral-7B sarcasm with LoRA, 4-bit quantization, and ~700 examples-because adding wit to chatbots is fun and useful.
A deep dive into Retrieval-Augmented Generation (RAG) and how it's revolutionizing AI responses by combining context-aware retrieval with sophisticated text generation.
A deep dive into the data preparation pipeline behind Gmail's Smart Compose feature
Insights and tips from 1:1 experience helping children with special needs or challenging behaviour learn to code through game-based, supportive, and flexible approaches.
After working on model-driven systems and facing real-world challenges, I've learned that simpler, smaller, and well-observed systems scale better than complex ones.
While learning Kubernetes, I discovered these Linux commands are used constantly for file handling, debugging, and automation.
A practical, developer-first walkthrough of LangGraph: when I reach for it, when I don’t, and how to ship agent loops/branches without the chaos.
Step-by-step setup of a 3-node Kubernetes cluster on AWS EC2 using kubeadm, containerd, and Flannel CNI, with security groups and region selection.
Models with just 135M to 7B parameters started outperforming their heavyweight counterparts on real-world tasks. Learn why smaller is smarter and how SLMs deliver 10x cost reduction with 5x faster inference.
How I wire Neo4j into AI systems: a developer-first take on knowledge graphs, queries that matter, and where graphs beat vectors.