Post #1401845

2026-02-04 20:55 UTC

The bottleneck was never writing code. It's understanding what to build. If you're using AI coding tools, focus on: • Smaller features (if it's 1000 lines, it's too big to review) • Clear acceptance criteria before you prompt • Tests first, AI-generated code second • Security audits (AI can't do this) More code isn't the goal. Solving real problems is.

Replies (4)

@mlevison@agilealliance.social 2026-02-04 20:55

Full analysis: https://agilepainrelief.com/blog/ai-generated-code-quality-problems/?utm_source=mastodon&utm_campaign=archive-reshare #AI #AIinSoftwareDevelopment

Open ##1401846
@weddige@gruene.social 2026-02-05 12:34

@mlevison I had a discussion with some developers about this last week. If we expect developers to take responsibility for the code they generate, the amount of work is capped by their ability to review code. And if we expect more (which is absolutely necessary, if we want the promised productivity gains), we can't blame them, if it goes wrong. If we celebrate huge productivity gains, we give up the right to complain, if AI fails. And it will fail.

Open ##1401858
@jose@mastodon.gamedev.place 2026-02-05 19:05

@mlevison this makes me wonder, it's then a viable way to do TDD? Humans authoring the tests, and AI implementing them.

Open ##1401864
@jrp@hub.kliklak.net 2026-02-05 20:46

@Mark Levison Right. it's getting hilarious, when you get AI to write code for audio coding applications. The machinery never understands, where you want to go, regardless of the detail you provide in your prompting. It's an endless back and forth, the code is often incorrect, and even more often not human readable or visible in applications, that have a procedural GUI. A complete time-waster actually.

Open ##1401867