Web Performance Is Scarier Than a Horror Movie
28 min read
A hands-on look at how web performance affects users and businesses, with practical improvements to images, video, fonts, Server Components, and Streaming SSR.
Posts
2026
React, Are You Still Alive?
11 min readReact news has been quieter than it used to be. But its recent updates and the community response show that React is not dead. It is taking on a different shape.
How Much Can You Trust AI-Written Code?
9 min readSince AI showed up, I write a lot less code by hand. So how much can I actually trust the code AI writes? A few practical devices I've come to rely on for building that trust, and the cost problem that comes with running them.
Reading Figures and Tables with Multimodal RAG
13 min readA text-only RAG can't read the figures and tables in a paper. I walk through how I built a multimodal RAG system that retrieves and answers from figures and tables too — building a paper-reading AI chatbot from scratch.
So, What Is Multimodal?
22 min readHow did AI go from handling only text to seeing, hearing, and drawing? I walk through the concept of multimodal AI, its history (CLIP), how inputs and outputs work across modalities, and even the trickiest case — video.
Taking RAG Further
22 min readWhen documents multiply and tables or images enter the mix, basic RAG starts to show its limits. I look at how to improve each stage of the pipeline — indexing (parsing, chunking, embedding), answer generation (query transformation, hybrid search, reranking, citations), agentic RAG, security, and evaluation.
So, What Is RAG?
16 min readRAG answers questions by retrieving external documents instead of touching the weights. I walk through the indexing and retrieval pipeline, then build a RAG system from a PDF by hand.
Fine-Tuning and PEFT
26 min readFine-tuning adapts an AI model to your domain. I cover how PEFT, LoRA, and QLoRA cut the memory cost, and when you'd actually reach for them in practice.
How Models Learn
23 min readA walkthrough of the inner loop — forward pass, loss function, backpropagation, update — with a small Python demo to train a model from scratch.
Attention Is All You Need — But What Does That Mean?
24 min readThe hardest part of studying AI was attention and the Transformer. Here I work through them by following the paper 'Attention Is All You Need'.
A Four-Year Retrospective
6 min readFour years as a developer, and the age of AI.