Observing the Probabilities
What I observed while training a tiny language model: the loss stopped falling, rug's embedding never moved, and cat and dog were not as close as I expected.
Technical
The Assignment Was One JPEG
What it actually takes to run a 38 FPS model on a Jetson Nano, and why mine ran at 12.
Viewing Language Through a Probabilistic Lens
How next-word prediction, distributed representations, and a neural probability model let useful structure emerge from language.
How I Access My Bare-Metal Homelab When I Touch Grass
Why I put NetBird inside Talos to reach my bare-metal homelab without depending on Kubernetes or another always-on machine.
How I Made My Homelab Declarative
Migrating every hand-installed Helm release on my Talos cluster into git with Argo CD: the app-of-apps bootstrap, the adoption drill, and the surprises each component threw at me, until helm list -A came back empty.
Working With Text Data
How raw text becomes something an LLM can actually train on: tokenizing, building a vocabulary, byte pair encoding, sliding windows, and turning token IDs into token and positional embeddings.
Understanding LLMs
A foundational look at large language models, recurrent and convolutional architectures, transformers, and the difference between BERT and GPT.
Why Your Pod is Pending: A Deep Dive into the K8s Scheduler
An in-depth look at how the Kubernetes scheduler works and a practical guide to diagnosing pods stuck in Pending state.
How etcd Works: Consensus, Quorum, and Failure Handling
A deep dive into how etcd implements the Raft consensus algorithm for distributed state management.
How Tailscale works under the hood
Understanding Tailscale's architecture with the help of my homelab setup.
Step by step guide on Manually Installing Arch Linux on Proxmox VE
Experimenting with Arch Linux installation to learn about secure, modular, and customizable Linux environments.
How My Homelab Helped Me Understand Kubernetes Cluster Architecture
Understanding Kubernetes cluster using my Homelab setup.