SRE insights, code quality tips, and startup tech advice. No fluff, just practical knowledge from 10+ years in enterprise infrastructure.
Everyone has an opinion about whether local models can replace cloud models for coding. I ran 300 benchmarks on Qwen3.8-27B against a corpus of 212,000 Claude runs. It tied Sonnet. Only two of eight comparisons survived the confidence intervals, and one of my own findings turned out to be a bug in my harness.
Read more →Installing an NVIDIA driver inside WSL breaks GPU passthrough. Here is why, and the toolkit-only setup that actually works.
Read more →A Homebrew build of llama.cpp silently ran on CPU instead of the Apple GPU, costing 7x speed. Here is how I traced it and the one-flag fix.
Read more →In December 2023, a new message format appeared in GPS Subframe 4, Page 17 — one that starts with the ASCII string 'TEXT'. 26 unique examples later, here is what the byte structure reveals.
Read more →12 million observations, 3,994 unique payloads, two distinct operational regimes. A statistical breakdown of how the military GPS key distribution schedule has changed since 2007.
Read more →Every GPS satellite broadcasts a 22-byte field that civilian receivers silently discard. For nearly two decades, that field has carried encrypted military key material. Here is what the public data shows.
Read more →Updated June 2026. This guide was originally based on 1,458 Python benchmarks. Since then, we’ve run 212,000+ benchmarks across Python, Go, JavaScript, and C#—testing chain-of-thought, politeness, personas, context pollution, model...
Read more →Should you write detailed CLAUDE.md instructions or compress them down to key phrases? The conventional wisdom says “be clear and explicit.” The Brussee CLAUDE.md toolkit says “compress everything, remove vowels,...
Read more →“This code controls critical medical systems. Errors could have life-or-death consequences.” If emotional stakes motivate humans, shouldn’t they motivate AI? The EmotionPrompt paper (Li et al., AAAI 2024) found that...
Read more →In April, we ran our capstone benchmark: 6,480 Python benchmarks showed the entire prompt optimization window was 1.4 points. Kitchen-sink instructions were the worst performer. Code-reviewer persona plus polite framing...
Read more →