|
|
|
|
|
|
by atq2119
1 day ago
|
|
|
As a non-GCC compiler developer myself, there's a spectrum of AI use and the words "AI generated code" can mean different things to different people. At the extreme ends, nobody I know well objects to AI auto-completion in your editor, but neither does anybody want to let AI open pull requests autonomously. Having a coding agent iterate on a well-defined narrow task in the background while I'm in a meeting or working on something else, and then doing a thorough, thoughtful, and active local code review (meaning, having an editor and the diff open side-by-side and liberally making edits to clean up the code) before pushing anything out for others to see feels like a reasonable point in the space right now. Nothing is perfect, but this style of active code review removes basically all AI smells in practice. The edit-build-test loop is fairly long (i.e., longer than a few seconds), so having AI babysit this loop for the initial development of a task is helpful. |
|
|
I think it’s more about turning language models into your smart intern, rather than letting them do all your work or become your moronic boss.
In any case, I do think there could be room for AI in the future—for instance, in academic research. I recently saw a news story about an AI that managed to detect certain types of cancer based on a specific blood test; I consider that a justifiable use of AI. However, using it to autonomously send PRs? That strikes me as going too far.