2026-07-22 21:23 UTC
@argv_minus_one@mastodon.sdf.org It's not the same task, but considering these amounts, I think some people should re-think their point of view that "human written code is good and AI written code is bad".
Obviously human written code isn't THAT good, otherwise AI would not find tons of bugs in it.
And if the developers had used AI while writing the code, maybe the bugs would not be found in production, but before release.
Years ago that was not possible, but nowadays it would be quite good for quality.
Replies (1)
-
@argv_minus_one@mastodon.sdf.org 2026-07-22 21:46
@borgbackup@fosstodon.org That's a non sequitur. Linters are also pretty good at finding bugs, but they aren't capable of writing code at all, let alone writing good code. It's also a non sequitur that bad human-written code somehow implies that AI-written code is better. It is entirely possible for AI code to be even worse. Finally, I'm not convinced that these stories of AI finding bugs are true. Last time I tried to use it for that, as I mentioned in , it failed miserably.