Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Open Chaos: A self-evolving open-source project (openchaos.dev)
405 points by stefanvdw1 1 day ago | hide | past | favorite | 83 comments




When I used to play Screeps[1], a MMO strategy game where you programmed to control your units and buildings, a group of us setup a player that was managed in this exact way called Quorum[2].

If anyone wants to run their own project in this way I open sourced the code to do so under the GitConsensus[3] project. There's a Github App (which may not still work, but if there's interest I'll restart it) and a "run it yourself" python library and CLI you can run from Github Actions[4].

1. https://screeps.com/

2. https://github.com/ScreepsQuorum/screeps-quorum

3. https://www.gitconsensus.com/

4. https://pypi.org/project/gitconsensus/


I don't get the title. Do I understand correctly this is basically "Twitch plays Github" without Twitch?

GitHub plays GitHub?


I'd expect even more chaos, let an LLM build the features and people vote.

I kind-of want to see an experiment going the other way.

Have a repo that has a committee of AI models deciding what to merge. Inform them of the goals of the project and that they should only allow positive changes but people are allowed to make adversarial PRs.

It can be more active because the committee can meet on demand. Then people and AI's can attempt to bend the project to their wills.



I honestly thought that this is what it was initially.

Is most code not written by LLMs these days anyway?

Most code by lines, perhaps, but not most code that works and is useful

Says who?

Says anyone who has tried to do anything requiring the smallest amount of computer science or computer engineering. These models are really great at boilerplate and simple web apps. As soon as you get beyond that, it gets hairy. For example, I have a clone of HN I've been working on that adds subscriptions and ad slot bidding. Just those two features required a lot of hand holding. Figma Design nailed the UX, but the actual guts/business logic I had to spend time on.

I expect that this will get easier as agentic flows get more mature, though.

Then the only place that novelty will occur is in the actual study of computer science. And even then, a well contexted agentic pipeline will speed even R&D development to a great degree.

One very bad thing about these things is the embedded dogma. With AI ruling the roost in terms of generation (basically an advanced and opinionated type-writer, lets be honest) breaking away from the standards in any field will become increasingly difficult. Just try and talk to any frontier model about physics that goes against what is currently accepted and they'll put up a lot of resistance.


I’ve been pleasantly surprised how useful it is for writing low level stuff like peripheral drivers on imbedded platforms. It’s actually-simple- stuff, but exactingly technical and detail oriented. It’s interesting that it can work so well, then go wildly off the rails and be impossible to wrestle back on unless you go way back in the context or even start a completely new context and feed in only what is currently relevant (this has become my main strategy)

Still, it’s amazingly good at wrestling the harmony of a bunch of technical details and applying them to a tried and true design paradigm to create an API for new devices or to handle tricky timing, things like that. Until it isn’t and you have to abort the session and build a new one because it has worked itself into some kind of context corner where it obsesses about something that is just wrong or irrelevant.

Still, it’s a solid 2x on production, and my code is arguably more maintainable because I don’t get tempted to be clever or skip clarifying patterns.

There is a level of wholistic complexity that kills it though. The trick is dividing the structure and tasks into self contained components that contain any relevant state within their confines to the maximum practical extent, even if there is a lot of interdependent state going on inside. It’s sort a mod a meta-functional paradigm working with inherently state-centric modules.


> a clone of HN I've been working on that adds subscriptions and ad slot bidding

Wut, what's the purpose of that? Is this just a toy learning project? Would it be to make money off of people who don't know that an ad-free version of HN exists at news.ycombinator.com? Will you try to sell it to Ycombinator?


A "clone" usually doesn't mean that they'll copy the content, but the idea, like Ola is a clone of Uber.

(Though they probably should've said a link aggregator instead of HN clone.)


I am hoping they are developing it as a satirical art project, otherwise... yikes; needing a credit card and an ad blocker to use HN would be very depressing and is counter to everything I enjoy about this forum.

I'm glad you are not being competent enough to create a paid version of HN with the help of AI

Says anyone with a modest level of skill at programming. It doesn't take a genius programmer to realize these things are terrible at writing code.

Not a developer by trade. But incidentally, today I took my first stab at "vibe coding". I wrote a little gui program to streamline a process that I've been doing for years. The code is an absolute wreck. But the program works and does what it's meant to do. I wouldn't ever expect anyone to maintain it, but for what it is, I can't complain. The alternative would have been for the tool to have not been written at all. The level of effort was so low that a) it passed the threshold of it being worth my time, and b) if it needs to be re-vibe-coded over again, then no worries.

The name of the person who said it is on the left above the comment.

Cool social experiment. It's interesting how narrow the scope of all top voted PRs are: change this or that detail in the voting (daily, count down votes etc), or make it more efficient (rust).

I wonder if this has the potential to build a "community" that will take this into a completely different direction, or if it will neatly stay within the initial boundaries.


Is it a kind of computer-assisted Nomic [0]?

0: https://fr.wikipedia.org/wiki/Nomic



Nomic vibes indeed

Really interesting. I wonder if something good will come out of it. It feels like twitch plays pomemon.

If you want to see a speedrun, I made the same thing around a month ago:

https://theboard.stavros.io


This is cool, but once a week seems a little slow


The frequency should be adjusted based on the number of participants

Request merging the change you wish to see!

It could merge any PR that reaches a set number of upvotes

is it forkable to have even more chaos?

Excited to see how this plays out, I made something similar a while back: https://news.ycombinator.com/item?id=9351286

Oh man, I was going to try and find that to link to it. I can’t believe it was 10 years ago… I really enjoyed following that for a while. Thanks for making it.

> The website IS the repo. The repo IS the website. I wonder if we get something productive by end of 2026 from this repo. Who knows, maybe we solve AGI

Would have been even more absurd if code AND PRs were all AI generated by different coding agents

Nothing is stopping that from happening tbh

It's not possible to generate anything productive this way.

Wikipedia basically works this way. And instead of it being directly public, it goes through a voting process. One might argue it's actually much more curated than Wikipedia :P

No, it doesn't work anything like this.

> One might argue it's actually much more curated than Wikipedia

Well duh. It's vastly more "curated" since Wikipedia isn't curated at all, almost anyone can change anything at any time but changes are supposed to reflect consensus (in theory, but there are numerous rogue agents who violate the rules) and it's a single instance with a linear set of changes that only occur once a week, whereas WP is a seething mass of constant change--but with a tight fitness function due to the (again theoretical) requirement that all changes must reflect reliable sources, not the whims of the editors--totally the opposite of OC. (There are additional policies and various governing groups but these make WP even less like OC). It's beyond absurd to liken OC to WP.


The end product is... just the website?

I feel like I'm missing something.


It’s an absurdist art software project, devoid of any consistent intent or purpose beyond the operating principles.

codified dadaismus

It can evolve into anything based on community votes

Just a website? Websites can do anything. It could evolve into a whole social network.

So it begins?

Once you have governance that people stick around for, you can decide to do anything


It's not a product, it's a social experiment for programmers.

They should automate reading hacker news comments and generating PRs to address them

Open a PR and suggest this.

You can't just "suggest" something in a PR, you have to provide the change.

Okay, open claude code, tell it to open a PR

Should votes get invalidated after major change in the ongoing PR?

Votes should remain. Have a criteria for invalidating candidates.

Anything beyond a certain age, and anything with unresolved conflicts gets stood down and requires a fresh nomination.


Not sure you can "cancel" github reactions of other users

Are guardrails, CI/CD, to make code at least compile-able and require minimal quality standards also possible to change via PR or managed somewhere else? With this possibility, it might went into oblivion indeed!

I mean.... it's the spirit of the project to eventually be able to reach to that state. I freaking love that project woaw hahaha

Firefox warns of a security threat when I visit the site.

Maybe Firefox is prescient, just waiting for someone to create a problematic pull request that does something untoward while simultaneously locking everyone else from submitting pull requests (and get a bunch of bots to upvote it in the last second before the merge window closes).

Merging the security threat is yet to be voted on

You know it’s kinda like a lottery the more I read it lol! If the repo got super popular and had lots of traffic say.

Am I the only one who's noticing that this "open chaos" project's most voted PRs are to add structure to the project (e.g., calculate +1/-1, etc.)?

I guess people just desire a certain amount of structure to their chaos :)


Can’t have one without the other

“Convenient chaos”

Reading through the comments, it’s remarkable how many of us have had the same idea at some point

Beautifully executed


Sorry to be a party pooper I just don’t get the point.

I don't think there's a point. You can always submit a point, if it gets voted you will have your point

This is exactly the point.

It's a bit like bigtech but instead of product people voting on what gets merged, everyone gets a vote here.

Twitch plays Github?

I guess this is one sign that coding is drifting to an art, given the LLM is invading.

A lot of engineering disciplines are a mixture of math, art, and science. Programming was no different, but I do think some people built up an identity that reinforced a difference that wasn't there to begin with.

This is a very interesting experiment where I hope the metamorphosis is more like a butterfly than Kafka.

Yes, this could end up either turning into a Linux or like when Microsoft released Tay and Twitter users taught it to be a Nazi. Or anywhere in between, really.

It really can't for numerous reasons, one of them being that PRs have to be fairly low effort, and this will be even more so if the popular "merge daily" PR is voted in. People talk about this "evolving", but it's nothing like biological evolution or genetic algorithms. It's just a linear sequence of small changes, and without either planning and central authority or some stable fitness function (the ecological environment in biological evolution) the changes are directionless.

> some stable fitness function

The participants could always vote to add a test harness and CI/CD to vet pull requests against.


That has nothing to do with a stable fitness function ... an external set of factors that determine which changes allow offspring to survive. This thing doesn't have offspring (or always has exactly one offspring and then the parent dies) and it survives until the whole thing collapses.

And I think they already have what you describe or something like it ... PRs have to build and survive CI.


It should have been abundantly clear that wasn't the way the word "evolution" was being used here to being with. (Actually the comment you replied to used the word "metamorphosis" so what are you even going on about?)

Nonetheless, if you're going to quibble that it isn't ahckchtually evolution because it's missing a fitness function then I'm going to counter that you can form a loose analogy so long as you have some fitness apparatus that's conceptually and operationally separable from the implementation itself. I think some unit tests and a CI pipeline is sufficient.


> It should have been abundantly clear that wasn't the way the word "evolution" was being used here to being with.

My whole point was that the sort of evolution that this will undergo isn't like biological evolution so it won't be effective the way biological evolution is. That should have been abundantly clear.

> Actually the comment you replied to used the word "metamorphosis" so what are you even going on about?

Did you ever bother to look upthread? I wrote "People talk about this "evolving"", and that comment was not a response to the one mentioning metamorphosis. See the title: "Open Chaos: A self-evolving open-source project"

I'm not quibbling and that's an offensive accusation as is your "ahckchtually" mocking as well as the rude tone of your clueless whooshes above so I will only respond you this once. Biological evolution has powerful mechanisms that this lacks ... in fact the biggest lack is that there's just one "organism" here, not a population, and just one change at a time. And your fitness function only determines whether something compiles and runs; it gives no direction to the "evolution" ... it's not being fit to anything that drives its progress (the choices come from the PRs, not from the fitness function, and they are independent of each other or at best loosely coupled--thus they aren't stable) which I explicitly pointed out previously when I mentioned the fitness function. So your "loose analogy" fails miserably and this thing is going to be directionless, as I said, and so it won't build up something like a Linux kernel or AGI (both of these have been mentioned, but hey, not in the comment that used the word "metamorphosis" -- apparently I have to say this).


confused, what is this and what’s going on exactly?

https://github.com/skridlevsky/openchaos?tab=readme-ov-file#...

Anyone makes a PR, there's a vote and highest voted one gets merged every week. It's marvelous.



Click through to the GitHub link at the bottom, which has the README. It explains everything.

Genius.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: