News for hackers. Stuff that matters.
Re:Being a Developer in the Age of Reasoning AI by righthand on Monday December 23, 2024 @12:26AM (#42492022)
Code is written to be auditable by humans, if you just generate machine code how will you know the level of correctness? Would you save the prompts then I have to prompt review before merge? That would end up being much wordier than a code file.
Re:Being a Developer in the Age of Reasoning AI by tasuki on Monday December 23, 2024 @02:33AM (#42492564)
Humans write the tests. AI writes the implementation. Just write good tests: property based. Or actual formal specification...
Re:Being a Developer in the Age of Reasoning AI by episteme on Monday December 23, 2024 @03:38AM (#42492850)
It's much quicker to write code than a formal spec for that code.
Re:Being a Developer in the Age of Reasoning AI by rootnod3 on Monday December 23, 2024 @07:47AM (#42494021)
Yes. Because at the end, the code should be the spec or the final source of truth for it.
Re:Being a Developer in the Age of Reasoning AI by tasuki on Monday December 23, 2024 @02:58PM (#42497144)
I disagree. The spec should be the spec. The code is just an implementation detail.
Re:Being a Developer in the Age of Reasoning AI by righthand on Monday December 23, 2024 @10:27PM (#42499511)
The style of the code is an implementation detail, once implemented it enters the realm of spec.
Re:Being a Developer in the Age of Reasoning AI by batshit_beaver on Monday December 23, 2024 @01:25PM (#42496484)
This right here is why I have serious doubts about the ultimate usefulness of LLMs in coding.

Code is the spec, and it's far faster to write the code yourself (if you know what you want to do and how to write code) than try to pass all this context to an LLM in the form of lossy and imprecise human language.

Re:Being a Developer in the Age of Reasoning AI by tasuki on Monday December 23, 2024 @02:58PM (#42497142)
Yes, especially so if you do not much care whether it's correct.