» Tag
software-engineering
75 postsWhen AI Writes Most of the Code, Peer Review Must Be Redesigned
As AI agents write and review most production code, traditional PR-approval compliance controls no longer reflect reality—here's what should replace them.
Teach Yourself Programming in Ten Years: Norvig's 1998 Essay
Peter Norvig's 1998 essay explains why true programming mastery takes roughly ten years of deliberate practice, not a weekend crash course.
Review-Loop Engineering: Designing Real Human Oversight for Agent Loops
Why 'human in the loop' isn't real oversight for AI coding agents, and how review-loop engineering designs packets that expose gaps, not just green checks.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comHow do you actually test if an AI understands your codebase
A hands-on benchmark for testing whether an AI agent truly understands codebase structure, tested across thirteen real Ruby projects.
Kani: A Model Checker for Rust Verification
Kani compiles Rust's MIR into CBMC's engine to prove unsafe-code soundness, functional correctness and panic-freedom, running thousands of harnesses in production CI for the Rust standard library.
Refactoring Cuts AI Coding Agent Token Costs by 83%
An experiment shows refactoring an AI-agent-built codebase cut input token costs for repeated code changes by 83%.
Building an AI Coding Workflow: The Right Agent at the Right Stage
A framework combining Shape Up, OpenSpec, and ADRs to split AI-assisted coding work between human judgment, agent drafting, and automation.
Five-Paper Series Formalizes Cohesion, Arrives at the IVP
Five Zenodo papers formalize software cohesion and derive the Independent Variation Principle, exposing gaps in common cohesion metrics.
AI Coding Agents Are Breaking Diff-Based Code Review
AI coding agents make diff-only code review unreliable; intent now lives in test names, builder APIs, and contract tests instead.
FOMO-Driven AI Coding: Speed Illusion, Hidden Review Debt
GitHub's 55% speedup versus METR's 19% slowdown finding reveals how FOMO-driven AI coding adoption hides the real cost of review and verification in mature codebases.