- python
- machine-learning
- data-science
- math
- code
- analytics
- automation
•
•
•
•
•
•
-
🗺️ Open Source Model Landscape: Benchmarks and Picking the Right One
A practical guide to the open-source LLM landscape in mid-2026 — model families, benchmark comparisons, size-tier recommendations, and how to pick the right model for your hardware and use case. Part 4 of the Self-Hosting LLMs series.
-
🥊 Framework Showdown: Ollama vs LM Studio vs llama.cpp vs vLLM
A hands-on comparison of the four main local LLM frameworks — what each does best, performance benchmarks, and which one to pick for your use case. Part 2 of the Self-Hosting LLMs series.
-
🔭 GitSanity: arxiv-sanity, but for GitHub
I built a personalized GitHub repo discovery engine that turns your own stars into a recommendation profile — so the good repos find you.
-
🖥️ Terminal System Monitors: Why I Keep Coming Back to htop
A five-year htop user tries btop, gets dazzled, gets confused, and finds out what actually matters in a system monitor.
-
🤖 Choosing Your Personal AI Assistant: Why I Landed on NanoClaw
After months of evaluating OpenClaw, NanoClaw, PicoClaw, and a dozen other frameworks, here's the honest breakdown — and why simplicity, security, and customizability led me to one clear winner.