On 27.07.26 10:24, Gard Spreemann wrote:
a person is still writing a precise set of instructions when they write C or JavaScript
I would contend that there are heaps of edge cases in both C and JavaScript where the intended meaning and/or the result is *not* precise[ly specified]. At all.
Yes, translating a more-or-less-correct/complete specification to code is (for the most part) not going to be one-shot and/or deterministic when you give the job to an LLM, but the same thing happens when you hand the spec to a junior programmer. The LLM might make more stupid mistakes or start out with worse assumptions, but on the other hand it'll happily write more tests — and it's not going to lose its motivation when you *finally* notice that glaring error in the spec and force it to throw away half the code it wrote last week …
-- -- regards -- -- Matthias Urlichs
OpenPGP_signature.asc
Description: OpenPGP digital signature
