alt Hacker NewsI think it's pretty simple - there's just so much more open source PHP code out there in the LLM's training dataset. Swift has been around for much less, and most Swift is closed-source - not that many years have passed since Swift has been able to run on non-Apple platforms, too.
Replies
psychoslave • today at 10:25 AM
PHP changed a lot since its early days. To the point where anything old would be considered bad practice by contemporary ecosystem point of view. So duration is not all. Comparatively, C seems to have stick to the same idiom all the way. That's not to praise C style form here to be clear, which is ridiculously obfuscating and feeling like pointless collection of linguistic awkward atrocities. But at least it's consistent in doing it.
I would also bet that 90% of Swift training data is UI code.
And UI code quality tends to be technically pretty crummy/low-discipline. Your UI code doesn't need much consideration around data races, for example.