zlacker

"Pull requests created by AI must have been fully verified with human use." should always be a bare minimum requirement.

>>alansa+(OP)
> "Pull requests [] must have been fully verified with human use."

I would expect this is entirely uncontroversial and the AI qualifier redundant.

>>alansa+(OP)
I would hope that actually testing the changes is done regardless of whether or not AI is used

>>alansa+(OP)
AI is so smart these days that I typically just ask Claude to verify the code for me.

This sort of request may have made sense in the old days but as the quality of generated code rapidly increases, so does the necessity of human intervention decrease.

>>Ntrail+F9
If you have good tests, certain types of change can be merged without manual testing. One problem specific to AI is that it has a tendency to game/bypass/nerf/disable tests, as opposed to actually making the code do the correct thing.

>>njhnjh+cG
If you care so little, why are you even prompting at all? Surely you can leave it to its own devices without troubling it with your wishes? It seems like the farther you go down this path, the more likely it is that it'll have something better to do.

>>njhnjh+cG
If you're going to put something on someone else's desk, you're going to have to own it.

If you don't check it yourself, then you're going to own whatever your tooling misses, and also own the amount of others' time you waste through what the project has decided to categorize as negligence, which will make you look worse than if you simply made an honest mistake.

>>njhnjh+cG
I literally just scrolled past a thread discussing the psychology of shamelessness and undeserved self-confidence that creates all this drive-by AI pull request slop wasting everyone else’s time and see this comment…

>>alansa+(OP)
> verified with human use

Quality of that verification matters, people who might use AI tend to cut corners. This does not completely solve problem with AI slop imo and solution quality. You ask Claude Code to go and implement a new feature in a complex code base, it will, the code might even work, but implementation might have subtle issues and might be missing the broader vision of the repo.

>>Retr0i+4R
that's why we have CI like GHA that runs the tests on PRs / commits

>>maxnev+Kf1
> people who might use AI tend to cut corners

People do this all the time too, and is one source for the phrase "tech debt"

It's also a biased statement. I use Ai and I cut fewer corners now because the Ai can spam out that boring stuff for me

>>njhnjh+cG
You still live under the impression that they are able to reason and verify it. Verification is done by doing it in The Real, not your or some llm's imagination (which is all their output, at best)