Bob McWhirter: Donβt Ship Infinite Monkeys
Bob McWhirter argues that open-ended agent exploration belongs in development, while shipped AI features must be bounded and proven on utility, reliability, budget and failure behavior.
Bob McWhirter argues that open-ended agent exploration belongs in development, while shipped AI features must be bounded and proven on utility, reliability, budget and failure behavior.
Andrew Lombardi wrote "Unit Tests are Not the Enemy" as a response to seeing people proud to remove verification from their codebases. That's removing the bad fire alarms, not addressing the fire, and he has suggestions for actually doing it all well.
Alberto Denia's artisan and engineer are a good lens on agentic coding: an artisan keeps his fingers on the code, and an engineer relies on the factory to make bricks. Both work, at different scales.
Alex Martsinovich argues that agentic coding causes four unavoidable harms - slop, alienation, deskilling, and team breakdown β but these aren't technological inevitabilities, they're the results of specific choices about how to use AI coding tools.
Kerry Ivan Kurian's 'Exponential Failure' says AI agents multiply parts faster than they improve them, so projects fail by arithmetic. He's right about the math and wrong about the fix: the answer isn't fewer parts, it's parts you can describe.
Jim Manico of Manicode Security showed OWASP London a disciplined approach to bootstrapping projects with Claude Code using scripted prompts that generate ARCHITECTURE, SECURITY, and CLAUDE files in sequence, each reviewed and committed before the next. His core rule: Claude never writes code directly - every change becomes a tracked GitHub issue first, giving developers review points and audit trails throughout.
Yury Selivanov recently released lat.md, a knowledge graph for your codebase, stored as user-editable markdown. The tool itself sounds useful enough, but checking it out and working out what it provides for your code was more useful than the tool's existence itself: effective agent management means going through an onboarding process.