#ai-coding
20 items tagged #ai-coding.
GUIDE 2026-05-11
Accept or reject? Five heuristics that beat 'looks right'
Most AI-assisted coding mistakes aren't bad prompts — they're suggestions that looked right and weren't. Five concrete checks that catch the failures before they ship.
GUIDE 2026-05-11
Code ownership when half the code came from an AI
AI-generated code is generally not copyrightable—but once you accept a suggestion, you own it. Here's what that means legally, operationally, and when something breaks.
GUIDE 2026-05-11
AI as a code reviewer: where it helps, where it's noise
AI review tools catch real bugs consistently but miss architecture, intent, and taste. Here's how to use the pair-review workflow without letting AI comments become background noise.
GUIDE 2026-05-11
AI coding and git: commits, branches, and the etiquette of an AI co-author
How to structure commits, branches, and attribution when an AI agent shares your keyboard — and the one habit that prevents merge-conflict headaches.
GUIDE 2026-05-11
Training a junior engineer in a workflow that already includes AI
Most juniors in 2026 arrive with AI tools already in hand. The risk is they never build the foundations those tools are hiding. Here is a curriculum that uses AI without letting it become a crutch.
GUIDE 2026-05-11
AI coding and strong type systems: where TypeScript, Rust, and Haskell help
Strong type systems give AI a faster feedback loop than unit tests. Here's why TypeScript strict, Rust, and Haskell make AI more reliable—and where looser languages let mistakes slip through.
GUIDE 2026-05-11
AI-generated commit messages: the times they're great and the times they're bad
AI handles the mechanical parts of commit messages well. The part it misses is explaining why a change happened — and that gap matters more than most people expect.
GUIDE 2026-05-11
Secrets, sandboxes, and network isolation when using AI coding tools
Three threat axes in AI coding tools—log exfiltration, tool-call leaks, and supply-chain poisoning—and the mitigations that actually reduce risk.
GUIDE 2026-05-11
Token economics for AI coding: per-model cost curves and where they break your budget
A breakdown of 2026 token prices across Claude, GPT-5, and open source models — and where autonomous coding sessions actually spend the money.
GUIDE 2026-05-11
Context window compression: the techniques and what they cost
Long sessions, paste-heavy work, and verbose tool output push context windows to their limits. Here are three compression strategies, what fidelity each one sacrifices, and a workflow that sidesteps the problem entirely.
GUIDE 2026-05-11
The AI debugging loop: stop fixing symptoms
AI handles the mechanical steps of debugging well. Root cause analysis is the step it skips. Here's how to force it not to.
GUIDE 2026-05-11
AI coding hallucinations: the four shapes they take and how to spot them
AI coding tools hallucinate in four distinct patterns. Knowing which kind you're looking at determines whether the toolchain catches it or a human must.
GUIDE 2026-05-11
AI coding in CI/CD: the few places it earns its keep
Most AI-in-CI integrations create noise faster than they create signal. PR triage works. Auto-review mostly doesn't. Here's where the tradeoffs land in practice.
GUIDE 2026-05-11
A decision framework for which AI model to use on which task
Most developers default to the most expensive model for every task. A four-axis framework—cost, intelligence, speed, context—shows when that's right and when it's 10x overpay.
GUIDE 2026-05-11
Pair programming with AI: three patterns, three failure modes
Three pair-programming patterns for working with AI—junior dev, rubber duck, second senior—and the one to avoid: letting the model lead.
GUIDE 2026-05-11
Spike mode vs production mode: two AI coding velocities for two purposes
AI coding tools are fast in both directions. The problem is that fast exploration and fast shipping require completely different operating modes—and conflating them is how spike code ends up in production.
GUIDE 2026-05-11
Where AI coding tools stop helping on legacy code
AI tools thrive on greenfield work. On legacy code with custom DSLs, undocumented invariants, and decade-old conventions, the instinct to modernize becomes a liability.
GUIDE 2026-05-11
Should the AI write the test, the implementation, or both? Three patterns
When AI handles tests and implementation together, it can satisfy itself without testing real behavior. Here's how to assign the work to get actual coverage.
GUIDE 2026-05-11
Cursor plus Claude Code plus Aider: when running multiple AI tools at once pays off
Most days one AI coding tool is enough. This is about the narrower case where running three in parallel — each doing the thing it was built for — actually earns its cognitive overhead.
