Yeah we all hear the main arguments… AI is bad because of slop content, stealing from creators, brain rot & brain damage, privacy concerns and most importantly… how billionaires are just using it for their own selfish reasons
But I’m asking about YOU 🫵 personally. The individual. What do you really think about AI? Do you care or are you indifferent? Has it actually affected your day to day life?
I find it’s perfectly possible to write large maintainable projects using these tools. I have a Rust project I built with LLMs that’s over 150k loc now, and it’s structure is a lot better than anything I would’ve ended up on my own. One of the things I do is ask the LLM to come up with a phased plan for introducing new features. I also ask the model to make mermaidjs diagrams I can inspect and come up with file layout up front. Then I get it to make a branch for each phase and implement a focused feature. Then I can review it and I have good context for what it’s supposed to be doing, and it’s scoped so that the code is manageable enough to fit in my head. Doing that alone gets you a long way. Another thing I do is ask it to make refactors by looking through the code base and finding repeating patterns in code that can be consolidated, or large files that need to be split up. If you do this regularly, you end up with much cleaner code, and the agent is much better at doing that at scale than you could by hand.
Testing is another really important aspect. I always ask the model to do TDD, and then add end to end integration tests for features. For web apps, using playwright storybooks is really effective. You can define exactly what the user workflow is and then have the model test it through a headless browser end to end. This creates a contract where you know what that functionality is actually working end to end.
As long as you don’t just let the model crap out tons of code unsupervised, and box it in sufficiently with a contract, then the code is no worse than what a human would produce. And I’d argue that it’s often better.
Openspec is along these lines and works well ime
Yeah it’s a nice tool, you really just need a bit of rails to keep the model on track I find. They’re good at doing well defined tasks, and if you have a plan where they just check steps off as they go, things tend to work well. I also found beads is a really handy tool for task tracking cause then you can just file stuff in there and instead of writing tasks in markdown you have a real history along with the status of the tasks. It solves the problem with markdown checklists getting stale.
good to know, I’ll check out beads. I was forced to start using Claude at work and had mixed impressions but once we started using openspec to keep it on rails as you say, it got hard to deny its capabilities.
I find I kind of look at the whole LLM + agentic harness setup as a genetic algorithm. Your tests and specs are the fitness function for the program you’re evolving, and the LLM is the mutator. At each step it generates some output, it gets tested against the fitness function, the LLM gets feedback and iterates on it. Eventually something working falls out in the end. The better you can define the selection criteria the more you box the agent in the better results you get.