[throw7272855]

Coding with AI falls in one of three categories:

1. The thing to be written is available online. AI is a search engine to find it, maybe also translate it to the language of choice.

2. The thing (system or component or function) is genuinely new. The spec has to be very precise and the AI is just doing the typing. This is, at best working around syntax issues, such as some hard-to-remember particular SQL syntax or something like that. The languages should be better.

3. It‘s neither new nor available online but a lot to type out and modify. The AI does all the boilerplate. This is a failure of the frameworks and languages to require so much boilerplate.

[tablatom]

I’m really happy to see this take. It’s not the first time but it’s not said often enough. I once had the thought that anything AI can do really well is probably something that should not be being done at all. That’s an overly broad statement but I think there’s some truth in it. The grand challenge of software engineering is to find beautifully elegant and precise ways to express what we want the computer to do for us. If we can find them, it will be better to express ourselves in those ways than to prompt an AI than do it for us, much in the same way that a blog written by an LLM is not worth reading.

[krackers]

There's another category (possibly a subset of 1), the implementation is novel but set of requirements is known and has a set of conformance tests so tight that the LLM can basically brute force its way to a solution. See e.g. the Claude Compiler thing. In this case it's less "search engine + translator" and more of "brute force search".

[Jensson]

How is a C compiler novel? There are so many open source C compilers. If you can download a bunch of different open source projects and they all work then it is not a novel problem, it is as solved as you can get already.

[nijave]

Really I don't think frameworks have kept up and LLMs are the hammer in Law of the Hammer.