About This Blog
Jun 26, 2026 · 2 min read
I started this blog for two complementary reasons. The first is to keep my own learning process as open as possible; the second is to take the knowledge I've picked up in a scattered way and give it a solid foundation by writing it down. AI is a field whose sheer pace can leave you feeling like you're perpetually "falling behind." I hope these posts can be both a space for me to think and a useful stop along the way for others walking the same path.
What you'll find here
I'm planning to organize the writing around two main axes. The first is deep technical posts: long-form pieces that build a concept from scratch, step by step, from intuition toward formalism. I imagine this is the part that will appeal to readers who want to engage with the subject from a more academic and engineering-minded perspective. The second is new developments: as you know, AI changes almost every day in the era we're living through. I'll share the lessons I draw from the papers I read or the news I come across, along with the bits of useful information I stumble upon that might save others some time.
Why I write
It's easy, as you know, to read about a topic and say "I get it"; but how solid that understanding really is often only becomes clear once we sit down to write.
You find out whether you've truly understood something when you try to explain it to someone else.
Writing is a process that disciplines thought. If you can convey a complex topic, or the intuition behind an equation, to someone in plain language, then you've truly internalized that subject; and if you can't, the act of writing itself usually reveals exactly where the gap is. Let's explore both AI and our own gaps together!
Welcome; I hope these posts help put a few things into place in your mind, too.
Want to know when a new article drops?
Get an email whenever I publish something new. No spam, unsubscribe anytime.
Comments
Related articles
Working Effectively with Claude Code — Part 2: Agents, Subagents & Multi-Agent Setups
Jul 15, 2026 · 11 min read
BPE (Byte Pair Encoding): What It Is and Why It Matters for LLMs
Jul 1, 2026 · 9 min read
Working Effectively with Claude Code — Part 1: Context, Skills & Prompting
Jul 1, 2026 · 7 min read
Building GPT From Scratch: A Step-by-Step nano-gpt Walkthrough
Jun 27, 2026 · 12 min read
What Is a Tensor? Linear Algebra for Deep Learning
Jun 24, 2026 · 5 min read
Attention, Explained from Scratch
Jun 23, 2026 · 5 min read
How Gradient Descent Actually Works
Jun 22, 2026 · 4 min read
Why Identity-Aware Negative Sampling Matters
Jun 20, 2026 · 4 min read