Get More Tokens per Second from llama.cpp
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 →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 →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 →Claude’s default docstrings are verbose. Functions get multi-line descriptions with Args, Returns, Raises sections even when the code is self-explanatory. The question: is this verbosity helping or just burning tokens?...
Read more →Our capstone experiment used Python-flavored kitchen-sink rules: snake_case, list comprehensions, docstrings, PEP 8. Those rules work great for Python. They actively misdirect C# code generation. When you tell the model...
Read more →Developers iterate. They generate code, run tests, fix failures, run again. The question isn’t whether to iterate — it’s whether the loop has signal. Blind “review and improve” prompts destroy...
Read more →Anthropic’s prompt engineering documentation calls verification “the single highest-leverage thing you can add to improve accuracy.” But WHAT kind of verification? We tested four strategies across 10,800 benchmark runs and...
Read more →Claude Code’s /init command generates a CLAUDE.md file automatically. It scans your codebase, extracts build commands, documents architecture patterns, and lists data models. It’s the fastest way to give Claude...
Read more →