The programmer skill is how to abstract the specs from all the examples. And then to formalize it. Actual coding is merely translation. And only beginners tend to focus on that.

Sounds very similar to what AI is good at.

May work for simple cases, but how would you come up with something like typst, or thunderbird?

I've yet to see AI be good at extracting good abstractions. More often than not it jumps to creating a battery of special case checks.

No. AI sucks at formal languages and implications.

Lossy decompression probably won’t ever be really good at this. If it’s missing from the data, then it won’t be there.

The AI math proofs were probably already out there in tiny pieces and nobody got all of the pieces together. That is valuable. It’s different from making a piece that is missing. And the AI will just hallucinate.

Interpolating between the examples still requires understanding of the domain for the interpolation to be a sensible one. And it’s an iterative feedback process: thinking about possible interpolations leads you to cases that need clarifications from the domain experts. The domain experts won’t come up with all relevant examples by themselves, and they typically aren’t as good at thinking about interpolations like a developer who is trained to always consider all possible cases; they don’t think in terms of models the way a developer does.

LLMs already have interactive discussions with me on the topics I engage with, including asking expansive questions, so I do not think this is beyond the realm of the technology.

Talking to CPAs never gets you to Pacioli groups.

Talking to engineers and mathematicians gets you there.