Comment by gtirloni
19 days ago
Spec-driven development is the only reliable way to work with AI. That's my current understanding. I spend more time refining the spec and bouncing ideas off of AI/team than before, which is good before there can't be any incorrect assumptions or hidden variables, otherwise AI will create suboptimal code. We should have been doing this much earlier in the process, even without AI, but now it's more necessary than ever. If you keep asking AI to make small changes as you learn about the business domain of your project, it will create a mess, in my experience. It's better to start from scratch and ask it to reimplement, if you finally understand all the requirements.
Sentiments like this make me wonder if perhaps the dream of the 90s was just ahead of its time. Things like UML, 4GLs, Rational were all being hyped. We were told that the future was a world where people could express the requirements & shape of the system, and the machines would do the rest.
Clearly that didn't happen, and then agile took over from the more waterfall/specs based approaches, and the rest was history.
But now we're entering a world where the state of the art is expressing your requirements & shape of the system. Perhaps this is just part of a broader pendulum swing, or perhaps the 1990s hopes & dreams finally caught up with technology.
Yes and no I'd say. It's still the case that now only by iterating and testing things with the AI you get closer to an actually good solution. So up front big spec will also not work so well. The only exception maybe if you already have a very clear understanding and existing tests (like what they did with the Claude's building the rust c compiler to compile the Linux kernel)
Worked a lot with UML in industry and academia.
I think PG said something about sitting down and hacking being how you understand the problem, and it’s right. You can write UML after you’ve got your head round it, but the feedback loop when hacking is essential.