> the analogy might be writing in assembler vs writing in your high level language of choice.
If it were deterministic, yes, but it's not. When I write in a high level language, I never have to check the compiled code, so this comparison makes no sense.
If we see new kinds of languages, or compile targets, that would be different.
It's a new type of development for sure, but with an agentic system like Claude Code that is able to compile, run and test the code it is generating you can have it iterate until the code meets whatever test or other criteria you have set. No reason code reviews can't be automated too, customized to your own coding standards.
Effort that might be put into feeling that you need to manually review all code generated might better be put into things like automating quality checks (e.g code review, adherence to guidelines) ensuring that testing is comprehensive, and overall management of the design and process into modular testable parts the same way as if you'd done it manually.
While AI is a tool, the process of AI-centric software development is better regarded as a pair-design and pair-coding process, treating the AI more like a person than a tool. A human teammate isn't deterministic either, yet if they produce working artifacts that meet interface requirements and pass unit tests, you probably aren't going to insist on reviewing all of their code.
> the process of AI-centric software development is better regarded as a pair-design and pair-coding process, treating the AI more like a person than a tool.
This is the part that makes me throw up in my mouth a bit, I'd rather pair with a human. But whatever, I'm old. You'll have to excuse me as as there are a lot of nefarious-looking clouds out there.
Sure, but the AI is faster & cheaper than a human, or even of a team of humans. So, if you are a solo developer and can't afford to hire a team of humans to help accelerate your project, you now have the option of using AI instead.
It seems the capability and utility of these models/products is increasing very fast. Agentic tools like Claude Code that run locally in your terminal and therefore have access to all your dev/test tools and environment is a huge advance since now the output isn't just code, it's fully tested debugged code, that passes whatever tests and quality gates you tell it are necessary.
At the same time that the tooling has improved, so have the models, and only very recently (last 6 months or so). People swear by Opus 4.5, and I've also been impressed by Gemini 3.0. A year ago I was also much more skeptical of the utility of AI for serious use, but they've improved a lot.
If it were deterministic, yes, but it's not. When I write in a high level language, I never have to check the compiled code, so this comparison makes no sense.
If we see new kinds of languages, or compile targets, that would be different.