Category: tech

0

Spec-First, Spec-Anchored, Spec-as-Truth: The Three Levels of Spec-Driven Development

Posted by

A practitioner’s guide to knowing which one you actually need. “Spec-driven” is not one practice. It is a ladder—spec-first (write then ship, spec often rots), spec-anchored (spec and code stay checked in CI), and spec-as-truth / spec-as-source (humans edit only the spec; code is generated). This piece maps the three levels (after Birgitta Böckeler on martinfowler.com), their tradeoffs, a cheat sheet, and […]

Read More →
0

CAVEMAN: Does Talking Like a Caveman Actually Make AI Better?

Posted by

A viral Claude Code skill claims to cut 65% of output tokens by making LLMs talk like cavemen. Two research papers suggest forced brevity can actually improve accuracy in large models. But tokens are also compute — and nobody has benchmarked whether caveman-speak helps or hurts code quality. A look at the arguments on both […]

Read More →
0

Beyond grep and the README: tools that map unfamiliar codebases

Posted by

Getting productive in an open source project usually means understanding someone else’s repository before you can ship a useful issue or PR. The default playbook is familiar: clone the repo, read whatever README or contributing guide exists, search the tree, skim recent commits, and hope the architecture becomes clear before you lose momentum. That path […]

Read More →
0

The LLM Vocabulary Sheet

Posted by

A plain-English reference guide covering the jargon that shows up every time a new language model drops, from parameter counts to quantization methods. Contents 01 · Architecture & Model Design — Transformer · Dense Model · Mixture of Experts · Active Parameters · Feed-Forward Network · Layers · Hidden Dimension · Attention Heads 02 · Attention Mechanisms — Multi-Head Attention · Multi-Query Attention · Grouped-Query Attention · KV Cache · Sliding Window Attention · RoPE · RoPE Theta 03 · Sizing, Scale & Counting — Parameters · Embedding Parameters · Non-Embedding […]

Read More →
0

DESIGN.md: a single file for design systems that AI can actually use

Posted by

Blurb: DESIGN.md is an open spec for encoding your visual identity in one repo file: YAML tokens plus Markdown rationale, a CLI for linting (including WCAG contrast) and exporting to Tailwind or DTCG, and a plain-text contract so coding agents stop improvising your design system from scratch. Contents When you ask a coding agent to build […]

Read More →