Mark LevisonFeb 4

AI is making us write more code. That's the problem.

I analyzed research papers on AI-generated code quality. The findings:

→ 1.7x more issues than human-written code
→ 30-41% increase in technical debt
→ 39% increase in cognitive complexity
→ Initial speed gains disappear within a few months

We're building the wrong thing faster and calling it productivity.

Show threadMark LevisonFeb 4

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.

Show threadjose
@mlevison this makes me wonder, it's then a viable way to do TDD? Humans authoring the tests, and AI implementing them.
Feb 5 at 7:05pmWeb
Show threadIan McDowallFeb 5
@jose @mlevison but tdd in this context will only work if you can write _all_ the tests, covering _all_ the edge cases, including security and performance.
And if that was possible, which I honestly doubt, you'd still be building up a black box system with potential problems in terms of architecture and understanding
Show threadMark LevisonFeb 5

@imcdowall @jose Early days. We're still learning.

I mostly use: https://github.com/PaulDuvall/claude-code --- I use /xspec to create the core acceptance criteria. I read and edit. Then use /xtdd to attempt to write the code. I keep all changes small and only commit what I can read and understand.