Feroan's Notes

Getting Started with Machine Learning

2026.10.24/1 min read

I've recently started learning machine learning, mostly trying to get a grasp of the fundamentals before jumping into the more interesting stuff. I've been learning Python for data science, working wi

I Don't Know What to Build

2026.10.19/5 min read

There's a particular kind of frustration that comes with wanting to build something and having absolutely no idea what it should be. Not because you can't think of anything. Quite the opposite, actual

Learning to Think in Steps

2026.10.16/2 min read

DSA · Problem Solving

I've started spending time on data structures and algorithms recently. Most of my coding so far has been around building projects, working with APIs, connecting different parts of an application, and

Getting It to Work Is the Easy Part

2026.10.09/2 min read

There's a point in building a project where everything technically works, but I'm still not entirely happy with it. The feature does what it's supposed to do. The API returns the expected response, th

Why Does Machine Learning Need So Much Math?

2026.10.06/14 min read

ML · Machine Learning · Mathematics

I started learning machine learning and immediately ran into a problem. Math. Not just one kind of math either. Linear algebra. Calculus. Probability. Statistics. Optimization. At some point, I starte

Stop Building Websites Like They're Apps

2026.09.28/10 min read

website · React · software architecture

There is a strange habit in modern web development: Someone asks for a website, and we start building an application. A few pages become a React application. Then we add a backend. Then a database. Th

Why AI Agents Need to Forget

2026.09.25/8 min read

AI · ai memory · context engineering

We spend a lot of time trying to make AI agents remember. Conversation history. RAG. Vector databases. Memory layers. Summaries. Bigger context windows. The general idea is simple: If an agent can rem

Your Docs Are Part of Your AI's Brain

2026.09.22/6 min read

ai agents · Documents · context engineering

I've been using AI agents to build software for a while now. Give an agent a repository, give it a task, and it can do some pretty impressive things. It can search through files, follow imports, call

I Thought Linux Was Hard Too

2026.09.21/7 min read

Linux · linux for beginners · distrohopping

For the longest time, I thought Linux was something only “really technical” people used. You know the type. Someone opens a terminal, types a command that looks like it belongs in a spaceship control

Your Website Works. So Why Isn’t Google Finding It?

2026.09.20/6 min read

Web Development · SEO

I had a website. It worked. The pages loaded. The links worked. The design looked right. I could open it on my phone, my laptop, basically anywhere. So naturally, I expected Google to find it. It didn

I Didn't Need DSA to Build My Projects. I Needed It to Get Hired.

2026.09.18/5 min read

DSA · Career · Technical interview

For a while, I thought DSA was one of those things you learn because you're supposed to. I could build applications without it. I could work with APIs, databases, LLMs, RAG pipelines, authentication,

I Keep Trying to Find an Excuse to Train a Model

2026.09.17/6 min read

finetuning · ModelTraining

I keep wanting to train a model. Then I start looking for a reason to train one. And that's where I get stuck. I can think of plenty of things I could build with an existing model. An API, a RAG syste

I Built an AI Runtime That Forgets Its Identity

2026.09.17/5 min read

llm · AI · local ai

Most AI systems have an identity. You deploy a model, give it a name, give it a GPU, and keep it there. Requests come in, the model handles them, and the system keeps running. I wanted to try somethin

Things I Thought I Understood Until I Actually Built Them

2026.09.16/10 min read

software development · AI

There is a strange difference between knowing what something is and actually understanding it. I have noticed it repeatedly while building projects. I can read about RAG, AI agents, databases, authent

What Building on Old Hardware Taught Me About Software

2026.09.15/7 min read

Everything Has a Cost I don't develop on a powerful machine. My main development laptop has 4 GB of RAM, limited graphics memory, and just enough storage to make me think twice before installing anoth

The Problem With Giving AI Agents Too Much Context

2026.09.14/8 min read

AI · context engineering · ai agents

When an AI agent gives a bad answer, the instinct is often to give it more context. More files. More conversation history. More documentation. More retrieved chunks. More memory. It feels logical. If

Why I Built Chronicles Without an LLM

2026.09.13/6 min read

AI · llm · Developer Tools · ai agents

There is a very tempting pattern when building anything around AI. You find a problem, add an LLM, give it some context, and suddenly it feels like the problem is solved. I almost did exactly that wit

Why AI Agents Need a Memory Layer

2026.09.12/4 min read

AI agents can read files, call tools, write code, run commands, and reason about problems. But there is still something they are surprisingly bad at: Remembering what happened before. A coding agent c