Posts
12 posts
Cloud ServicesMay 3, 2026GPUs Explained, Part 3: The Hardware Behind Modern AI
What an H100, H200, B200, and a GB200 NVL72 rack actually are. Plus HBM, NVLink, training vs inference, and the alternatives like TPUs and AMD MI300X.
21 min read
Cloud ServicesMay 2, 2026GPUs Explained, Part 2: Inside a GPU
What is actually on a GPU die. Streaming multiprocessors, CUDA cores, threads, warps, memory hierarchy, and tensor cores, in plain English.
17 min read
Cloud ServicesMay 1, 2026GPUs Explained, Part 1: Why AI needs GPUs
A simple story of why every modern AI service runs on GPUs and not CPUs. From mainframes in the 1950s to the H100, written for software engineers.
19 min read
LLMApril 27, 2026Open weight models you can download, use and even modify with your own data
A snapshot of who's shipping what in open-weights LLMs right now: parameter counts, architecture, context length, license, and whether the weights are really open or just open with friction.
11 min read
AI AgentsApril 8, 2026You Probably Don't Need an AI Agent
Everyone's throwing LLMs at problems that don't need them and calling everything an agent. Here's a simple way to think about what goes where.
5 min read
LLMApril 1, 2026How Much Should You Trust What an LLM Tells You?
I fine tuned a model on 50 wrong answers to see what it does with a question it hasn't seen. The result changed how I think about trusting AI.
25 min read
LLMMarch 24, 2026LLMs Explained, Part 4: The Platform Era
From GPT-4 to today's reasoning models, agents, and coding tools. How LLMs went from a single chatbot to the platform every product is built on.
10 min read
LLMMarch 20, 2026LLMs Explained, Part 3: How LLMs Got Useful
From GPT-3 to ChatGPT. The story of how scale, instruction tuning, and human feedback turned a text-completion engine into the assistant a hundred million people started using overnight.
10 min read
LLMMarch 16, 2026LLMs Explained, Part 2: How the Transformer Works
How the 2017 'Attention Is All You Need' paper threw out the RNN, what self-attention actually does, and why this one architecture became the foundation of every LLM today.
14 min read
LLMMarch 12, 2026LLMs Explained, Part 1: How We Got Here
A simple history of AI from 1950 to 2017, written for software engineers who want to understand where today's LLMs actually came from.
15 min read
Neural NetworksMarch 8, 2026Interactive demoHow Neural Networks Work
Plain english walk-through of neurons, layers, training, and embeddings. The fundamentals you need before any modern AI article makes some sense.
10 min read
LLMMarch 5, 2026Updated April 29, 2026What Even Is AI Right Now
A plain english map of the AI world for tech professionals. What an LLM actually is, how RAG works, what an agent is, and where to start if you want to move your career toward AI.
28 min read