Blog
Something worth reading.
Notes I've written by hand — not generated. Web development, design, the messy middle of building things, and what I'm learning as a Full-Stack Engineer building AI-native products. Written by Nabin Khair.
The Real Recipe for Building Apps With AI in 2026A practical recipe for building real apps with AI in 2026: specs, harnesses, and the security checks most guides skip. Written for coders and non-coders alike.
Loop EngineeringPrompt engineering was about asking the right question. Loop engineering is about building the system that never has to ask.
Understanding AI Harness EngineeringAn agent is a model plus a harness. The model does the thinking. The harness is the part you actually build.
Why LLMs Hallucinate, MechanicallyHallucinations aren't a mystery. They're the predictable output of how these models are trained, evaluated, and wired internally.
Context Engineering for AgentsPrompt engineering taught us how to talk to a model. Context engineering is the harder craft of deciding what an agent sees on every turn of its loop.
Killing a Process on a Port, ProperlyWhat a stuck port actually is, why TIME_WAIT and CLOSE_WAIT happen, and how to free the port without leaving a mess behind your app.
What is an LLM Distillation Attack?A method of extracting knowledge from an LLM by training a smaller model to mimic the behavior of the larger one.
Bypass Vercel's GitHub Auto-Deploy Restrictions Using GitHub ActionsDeploy to Vercel from organization repos on the free Hobby plan using GitHub Actions and a single git config trick.
AI Coding Agents & the Future of DevelopmentDeveloping products using agents is the future of software development.
Stop Wrapping APIsReal products solve real problems, not just repackage AI models.
Git Recovery GuideA practical reference for rescuing work when Git history goes wrong.
What is Vibe Coding?Explore Vibe Coding, Andrej Karpathy's revolutionary idea.
AI-Powered IDEsComparison of VS Code forked projects like Trae, Cursor, Windsurf, and Pear.
Understanding LLMsDeep dive into the working and use cases of Large Language Models.
Web Storage ObjectsAn overview of web storage objects and their use cases.