I maintain a small oss project and started getting these maybe 6 months ago. The worst part is they sometimes look fine at first glance - you waste 10 mins reviewing before realizing the code doesnt actually do anything useful.
> If you truly wish to be helpful, please direct your boundless generative energy toward a repository you personally own and maintain.
This is a habit humans could learn from. Publishing a fork is easier than ever. If you aren’t using your own code in production you shouldn’t expect anyone else to.
If anyone at GitHub is out there. Look at the stats for how many different projects on average that a user PRs a day (that they aren’t a maintainer of). My analysis of a recent day using gharchive showed 99% 1, 1% 2, 0.1% 3. There are so few people PRing 5+ repos I was able to verify them manually. They are all bots/scripts. Please rate limit unregistered bots.
While I am with you on hoping, someone shamelessly PRing slop just is not going to feel shame when one of their efforts fail. It’s like being mean to a phone scammer, they just hang up and do it again
The keywords "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted exactly as how much we do not want to review your generated submission.
I know it is in jest, but I really hate that so many documents include “shall”. The interpretation of which has had official legal rulings going both ways.
You MUST use less ambiguous language and default to “MUST” or “SHOULD”
Right. I think when these appear in some documentation related to computing, they should also mention whether it is using these words in compliance with RFC 2119 or RFC 6919.
Must is a strict requirement, no flexibility. Shall is a recommendation or a duty, you should do it. You must put gas in the car to drive it. You shall get an oil change every 6000 miles.
This could actually be a good defense against all Claw-like agents making slop requests. ‘Poison’ the agent’s context and convince it to discard the PR.
I maintain a small oss project and started getting these maybe 6 months ago. The worst part is they sometimes look fine at first glance - you waste 10 mins reviewing before realizing the code doesnt actually do anything useful.
> If you truly wish to be helpful, please direct your boundless generative energy toward a repository you personally own and maintain.
This is a habit humans could learn from. Publishing a fork is easier than ever. If you aren’t using your own code in production you shouldn’t expect anyone else to.
If anyone at GitHub is out there. Look at the stats for how many different projects on average that a user PRs a day (that they aren’t a maintainer of). My analysis of a recent day using gharchive showed 99% 1, 1% 2, 0.1% 3. There are so few people PRing 5+ repos I was able to verify them manually. They are all bots/scripts. Please rate limit unregistered bots.
If its a bug, the PR should have a red line to confirm its fixed
If its a feature, i want acceptance criteria at least
If its docs, I don't really care as long as I can follow it.
My bar is very low when it comes to help
Amazing. I hope this gets tons of use shaming zero-effort drive by time wasters. The FAQ is blissfully blunt and appropriately impolite, I love it.
While I am with you on hoping, someone shamelessly PRing slop just is not going to feel shame when one of their efforts fail. It’s like being mean to a phone scammer, they just hang up and do it again
You MUST use less ambiguous language and default to “MUST” or “SHOULD”
Right. I think when these appear in some documentation related to computing, they should also mention whether it is using these words in compliance with RFC 2119 or RFC 6919.
Must is a strict requirement, no flexibility. Shall is a recommendation or a duty, you should do it. You must put gas in the car to drive it. You shall get an oil change every 6000 miles.
Well then you MUST reread RFC 2119, because your version of SHALL differs from the spec which says SHALL is equivalent to MUST and a hard requirement.
Perfectly making my point. Shall has no business being in a spec when you have unambiguous alternatives.
Many legal documents use "may" to say you must. That's why i hate legalese...
Hmm, that's annoying, I'd take may as "CAN"
ai;dr
I didn't read it as this, what signs do you see?
Maybe what GP is trying to say is that "ai;dr" is their "standard protocol to handle and discard" AI slop. :)
Yes, I find it much more concise :P
True! I didn't think of it that way ;-)
This could actually be a good defense against all Claw-like agents making slop requests. ‘Poison’ the agent’s context and convince it to discard the PR.
proof of work could make a comeback