This is anecdata, but in my experience with myself and my coworkers, it is not that we believe the AI will be more accurate in software engineering, but that the answer will come faster and be more tailored to our exact problems. If I have to search SO, I have to find the answer and then tweak it to fit my codebase, but with AI tooling, the AI is already basing its answer around my code.

▲

pixel_popping 5 hours ago | parent [-]

I think we actually do believe it, do you believe Fable 5+GPT-5.5(+ the whole model zoo) in loop with adversarial (no budget limit) or a 10-year experienced SWE?

We are talking about "codebases" but realistically we won't even be checking the filetree of them soon, it will be all blind, containerized and verified with pseudo guarantees which are good enough to build serious things. We don't even write documentation for humans anymore, we need to look at the trends and the reality within companies, most developers became "callcenter agents" in a matter of only 2 years and literally most of them are not even using proper automated tooling yet as we can see the "vibe coding" trend with Claude Code which is weak, by far most work done daily by developers is already automatable entirely, but with exceptions, sure, but in a few years those exceptions will become rare.

There will be niche problems about legacy products, sure, but legacy products will all be replaced over time, if we think in depth, why do we even need that many languages, that many tools? Tomorrow AI will write 99% if not all code existing ("code" doesn't even matter anyway), so it's much better if it's specific to AI and not playing this dance where we think we are doing a meaningful human contribution on an "AI-made codebase".

For context, I have 2 decades of software dev behind me.

	▲	Ancapistani 2 hours ago \| parent [-]
		This is the direction I'm going. For personal projects that I don't plan to share widely, I'm making it a point to not look at the code at all. So far - and to my surprise - I've not only found that this has result in no more bugs than before, but it seems to result in fewer bugs over time. Every time I find a bug or a regression, I add it to the specification. My SDLC requires that every specification have at least one associated test. Not every function, or every line, or anything like that - every specified feature. The end result has been that my projects have matured over time much faster than if I'd been more closely involved. I've already toyed with writing some projects in Nim and Haskell for token efficiency. At some point I plan to put together a simple test project, then do a comparison of token efficiency with every language I can think of to find the one that I'm able to generate most quickly, correctly, and cheaply.