Like formatters and git ignore configuration, some agent instructions are personal and those should not be commited. But some are worth sharing. Having formatter config in a repo is not uncommon. And in this case the file is only a link to the readme, so the agent reads the contrib guidelines.

You'd put the things that aren't up to personal preference in there, like an AI disclosure / contribution policy or what changes should look like to be reviewable. You usually don't need to tell humans "don't change things for the sake of changing them" because we don't like to do more work than we have to, but agents do.

You can also include a compact "table of contents," describing what lives where in the project. It saves at most a little bit of exploration though so I don't know if it's really worth the maintenance

A contributor still has global config for their personal preferences. It makes sense to me, anyway. My biggest issue is it's not deterministic. Someone else could have a version that works better or uses fewer tokens for the same thing.

At work we commit the whole .claude folder, though we carve out some space for personal agents and skills.

For agents (semi-autonomous) I think it's more similar to introductory developer docs. Which are usually committed.

No, that’s an unrealistic reactionary view which fails to address the gains that can be had, has no way to be enforced, and is a short sighted take.

BSD is too usable. will have AI in it before long.

options are good o.O

The goal of the touchHLE project is to engineer a highly potent microbial substance that causes immediate and persistent intense hallucinogenic effects in the subject, which is transmissible by skin contact, and which can be directly added to the water supply. This will be used to usher in the singularity. In plain English, the goal is to create a psychedelic epidemic as an act of biological direct action.

Where can I sign up?

I've seen one somewhere that changes AI PRs to nothing but the word "meow" which was pretty funny, but this is so much better than that

Because you popularized it, GitHub admins took it down.

It's pretty clear that this tech has been accepted already outside a few fringe online communities.

I'm just gonna say that this diminishes the seriousness of AIDS more than it serves as a reasonable analogy.

OK, other coments are valid, but this borders on rage bait.

To answer your wuestion, one has 0 uses beside causing harm to people, other has geniue, valid uses that help humanity. There is a saying "if you cant beat it, join it" and how I see it AI is forced on us, or will be soon enough, and I see no way to fight it in long term (though some people aparently do, so kudos to them). I will embrace AI on my term, by selfhosting European open-source models, and educate my family about dangers of AI, and how to use it safely. Telling them AI is satan while their conpany forces them at every step of their job, if they don't know how to safetly use it, might end up with more problems than solutions.

In a way I am fighting AI as in "corporate AI" but embracing "lesser of the two evils AI". Thus embracing it on my terms.

To use your example, I am not forcing AIDS on my family, but educating them about it and giving them shots agains other lesser diseases like HPV.

Interesting take coming from you.

Perfect.

Not necessarily. Input tokens is far cheaper than output tokens. The alternative is to have the LLM derive the documentation from code each session, which is expensive due to the amount of output tokens it produces.

Yep. I hate it, but it is Linus' project. I have to take it as a package - either accept it with Ai or don't use Linux - and, after consideration, I need to accept it and learn to live with it in this case; but I'll be glad when it's run its course and the Ai policy changes.