the computer under your desk!
Roll your Own, don't depend on billionaire platforms to get your work done...
Orchestrating an agent free for all tends to invite more chaos management.
At the same time there’s folks who quietly have this working.
25k seems like a small bounty for such a large prize.
https://www.cloudflare.com/git-competition/?cf_page=next-git...
The human wallet
I’m tempted to ask an agent to submit an entry for me.
What an offensive slap in the face.
Tone deaf to the nth degree.
This is basically aimed at AI startups who are in SF anyways and need a platform for marketing. So no shortage of contestants.
I don't have a strong opinion here, but giving away compute as a prize for hackathons isn't anything new.
So, would it maybe make sense to question this whole bit, before we starting creating platforms for something like that?
Why do you need hundreds of thousands of agents working on the same codebase? In my experience, and what I see around me, quality code that actually works in production isn't produced by "software factory autonomously run by 1337 agents", but instead one human sitting and interacting with maybe 1-3 agents max, back and forth, pair programming rather than letting hundreds of them output million of tokens over hours.
Are others seeing the same thing, or am I in my own little bubble here? All the "software factory with agents" approaches I've spent time looking into, literally produces trash on top of trash, while I see senior developers 10x their productivity while producing better code than before and they have one terminal open with three panes, a text editor, a agent TUI and a general shell, that's it. Is what I'm seeing (and doing myself) not the typical situation out there in the wider world?
But I don't think it's actually a good idea. Keeping everything on the same version is difficult. We have package managers that do a better job.
Not to take anything away from your point, but TFA said hundreds or thousands - not hundred of thousands. Couple orders of magnitude of difference there…
You’re still spot on - even thousands of agents working on a single codebase would mean hundreds of humans directing them…
Cloudflare is perhaps most famously and most significantly an international, global platform. That's kind of the whole point.
Only in the smallprint does it mention you must be a United States or Canada resident to enter.
https://en.wikipedia.org/wiki/Google_Wave
https://youtu.be/v_UyVmITiYQ?t=3850
https://www.usenix.org/legacy/event/lisa09/tech/slides/berli...
We're now in a world where we expect real-time interfaces to be developed and immediately deployed for our feedback by agents, in business-critical settings where classic SDLC timelines are far too slow, but code quality is becoming more difficult to manage at scale.
Git, at its core, is a fundamental notion that behavior is an auditable tree of immutable changes, where any participant can rearrange or rewind or remix this sequence on a local machine to show, and interact with, a provisional combination of those changes.
Google Wave, with its operational transformation (OT) and federation systems, was similar in many regards. We have CRDTs now, and far better techniques for auto-merging workstreams - including agentic systems that can resolve conflicts intelligently!
Wave fundamentally had a concept that people would come together and evolve a simple chat interface, into a customized real-time application for their use cases, and that that iteration could happen in real-time, with data and behavior both evolving in collaboration with bots. Wherever Git and the broader notion of SDLC goes, I hope it brings the best of this thinking.
Throughout it's existence Google has been revered as a company for its engineering output, but if you interrogate that even a little bit, you end up with a very small minority of gems among a massive ocean of over engineered crap. Even the huge objective open successes like k8s are to this day sold with the massive caveat of "it's heavy & over engineered, but": nobody's calling k8s elegant. Pretty much all of their good products are acquisitions, many of which they've subsequently degraded.
One can certainly make this argument about almost any large corporation, but I do think there's very few with such a stark divide between how the quality of their engineering work is revered & the reality.
They were around 10% in Europe when they ramped down everything.
It was the option for those unable to buy iPhones, and not willing to use Android as alternative.
However we had the whole mess with Windows 7 to 8.0 being a full reboot for devs, 8.0 to 8.1 being a reboot, 8.1 to 10 yet again, which naturally meant no one cared with quality apps as well.
Google+ was pure garbage being shoved down our throats. That was a huuuge signal that Google had changed.
I think that was maybe a secondary problem with Wave: it was marketed as some new voodoo that ended up smelling like a hammer seeking a nail, when it was really just Email 2.0
Amazon hasn’t built anything innovative since the Kindle.
Surely it’s a consequence of being publicly traded that these companies cease to be able to develop good novel products rather than acquire competitors or iterate on past successes.
The number of products under the AWS that are more impactful to society and more profitable to Amazon is vast.
That was in 2007; S3 and EC2 were in 2006. The pace of innovation at AWS has declined, which is partially to be expected as it matures.
https://en.wikipedia.org/wiki/Media_Temple probably counts, too. They had auto-provisioned VPSes long before EC2. I'd also count VMware ESX.
Gmail could operate as it always has, being an email client that integrates with every other email client. But when a Gmail user emails another Gmail user (or a group of them), have the thread automatically turn into a Wave, with everything that entails. This gets the new features where people already are, creates an incentive for people to move their email to Gmail, and doesn’t create yet another inbox for a person to manage.
I always saw Wave as a business failure, not an engineering one, for this reason.
What Meta got right with Muse - https://news.ycombinator.com/item?id=49946526 - October 2026
In an ideal world you're right, but I still think it was an engineering failure as, theoretically, it should be easier to make something usable on a greenfield project, & it was a horrific mess.
https://theappslab.com/2009/10/05/google-wave-the-aftermath/
So they would have needed to invest in native mobile apps, and in significant levels of optimization. And none of this, not web or mobile, had the developer experience necessary to iterate quickly enough as the UI would inevitably evolve upon contact with customers, and you'd end up having many widgets reflecting a centralized global state.
Not to mention that you needed sticky server-side sessions to run the operational transformations efficiently, which harkens to the KV caching challenges that still challenge us today.
But it was an incredible dream, and it was a key source of inspiration to me to choose CS as a path.
The way they code Java, the C style C++ in some parts, the Android Studio stable releases that are always as buggy as preview releases (to the point of becoming a meme among Android devs), and so on.
Can I question the quality of said hiring practices?
I have been rejected for a project that was starting from scratch on something exactly like I had been building for 6 years at a competitor, based on such famous hiring practices (not at Google though). I was literally more experienced than the whole team on what they were building.
Because you hire people who are really good at leetcode doesn't necessarily mean that you always get the best candidates for the job?
Advice for everyone considering this: if you're passionate about ideas in this space and have access to an LLM — build it yourself and start your own company. In fact, message me easting.exe [at] gmail. I'll throw in $25k to get us started. I'm a prior founder with an exit. Because this offer from Cloudflare is ridiculous.
Single point of failure, for both technical and political failures.
One remembers that during the vast stretch of time that Cloudflare wasn't offering the new whiz-bang service, one was doing just fine in one's endeavors.
If one is fine with CloudFlare being the MITM for most of the Internet, then this doesn't matter at all to you. But if that or any other aspect of how CloudFlare does business and what their capabilities allow them to do concerns you, then that's how one begins.
Do you want the pain now or later?
We want more Cloudflare.
I am curious what people think about the use case that is different for AI agents compared to humans. Aside from the things people use SCM for already that is.
Fossil fits the bill if you ask me because it has built in forum and stuff too, so Agentic discourse can happen there, commits happen in the SCM history. And it has auto sync so they can automatically sync their state.
But I love fossil for this. You can create users for all of the agents (or agent roles). The CLI for fossil is just a binary and it compiles nearly everywhere.
+1 over here for agentic fossil. With fossil the "work" is integrated in with the code. Beads separates this out, the beads are instances of work that agents can consume, and they aren't part of the work repo. I could see why you might want this, but I still think that fossil gives you more utility.
More info on beads if you are curious: https://github.com/gastownhall/beads
So if I wanted to use fossil scm, i'd have to find a way to glue that on, and now ... we'Re basically in the same situation as with any other solution: it supports only a subset of the feature we want.
and especially CI pre "merge" is a hard requirement, and fossil doesnt have any concept for that i think?
But the last time i evaluated it was in the mid 2010s, so things may have progressed since? but couldn't find anything on cursory glance and AI confirmed that position, but we all know how often its wrong... so how did yall solve that issue?
Strangest tech announcement ever.
None of this is very clever or very compelling.
Whoever in Cloudflare thought that this is an appropriate compensation for the work is delusional. This is insulting.
Even when we cram the collaboration ledger into git notes, git's optimistic locking still breaks down in a thundering herd scenario, which is now easy to spin up in a git-centric agent collaboration scenario. I think the decision ledger in git needs to stay separate from the collaboration ledger, and both need massive elastic scaling capabilities when we as an industry are still used to thinking of scaling in a pre-agentic world. Think what happens when in the near future non-technical users are the dominant users of fleets of agents, they are virally connected in a social media frenzy, and descend upon a repo. Billions of concurrent agents all trying to do something with a repo and affiliated forks, are not hard to imagine in such a scenario.
I build them on machines I own placed in racks I have they key to.
There aren't any resource limits to hit and legal service is brought directly to me - not to a provider nor middleman.
There also isn't a global MITM inserting itself between me and my users.
I can't imagine doing it any other way and I implore you not to build things on complex, fragile, highly abstracted foundations.
Cloudfare buys a lot of posts here*
I'm a cheapskate so am sometimes motivated by this cheapness, but each time I realise it's easier to just stick with what I know (Linux daemons) than cloud offerings.
Do you have any suggestions for something in the homelab/self-hosted space where CloudFlare has great offerings? (Other than the boring stuff like cache/DNS).
a few years ago it was exciting to read their product launches - and to use them.
Now it feels like a wave of slop. They do whatever next thing is trending on twitter. fs for agents? sure! new git? sure! agent os? Sure!
like there is absolutely no filter. whatever pops in their mind they push it. and the results are mediocre at best.
I agree some of the latest stuff feels slop-py, but the core offering is extremely good.
Now that we don't have to worry about people and weak git skill getting in the way, agents can use git without needing all the emergent centralization.
Anybody else remember when a less evil version of Google gave their engineers time to go make whatever they wanted to make? And everyone was like that's really cool — to trust your smart people to make useful things.
Every half-baked product coming out of Cloudflare feels like some version of that. Letting your engineering teams cook to see if the end result tastes good. Some stuff doesn't. Some stuff is amazing.
Now I have DNS, Workers, D1, R2, email, secret vault, MCP, CLI, tunnels, access, analytics, and on and on. I have like 8 Svelte apps running with decent traffic for free. And they're stable. And it feels like Cloudflare is loss-leading instead of conducting bait-and-switch enshittification. I've been using their shit for over a decade.
Looking around the rest of the industry landscape, I'm not sure how anyone lands on Cloudflare being bad for developers/engineers. My shit is centralized because nobody else does what they do and delivers the DX that they do. I truly feel gaslit sometimes on this site.
Yes, it was great. Until Google turned evil, and the goodwill that we had given to them on the basis of all of these cool products was turned back against us. The lesson I learned from this time was that you don't give a company leverage over you just because you like what they are doing today. You should also consider where they are headed in the future.
Why did Google turn evil? Do you think Cloudflare is immune from these same incentives? Is giving a bunch of free services away to everyone sustainable, or will they be forced to tighten the screws in the future, and if so, what will it look like when they do?
Businesses only care about money. That's why the Cloudflare hate feels strange to me I guess. They've been giving stuff away to devs for free that would normally be expensive, and supporting open source projects at the same time. They're not perfect but this is capitalism. Everyone sucks in some way or another. They're conducting business but at the same time, they're driving their business with loss-leading services that they're definitely losing money on. That's not a business practice I would typically attribute to an evil and soulless money machine. I'm not naive either, I've been waiting for them to begin enshittifying for at least 5 years. They just never seem to.
It's not free, it moves the cost onto the users of those services. I have to pay with my time and my data.
Or, increasingly, I hit backspace as soon as I see the Cloudflare logo. Who's going to pay when the users don't?
But part of the story is that they also protect the DDoS providers causing the problem! To some extent, they're the firefighter arsonist who suspiciously always is first to arrive on scene to be the hero. Recent example: https://news.ycombinator.com/item?id=48025001
They had a very hard line on refusing to take anyone off their platform without a court order. There was a huge fuss here (https://news.ycombinator.com/item?id=15031922) when they told the Daily Stormer (https://en.wikipedia.org/wiki/The_Daily_Stormer to go elsewhere.
The funny things is, I'm actively working on a replacement for Github but it's not gonna be built on Cloudflare LMAO!
It's not gonna be ready by CLoudflare's deadline but I'm aiming to get the beta deployed by end of November. Plenty to do! It'll be available on eol.sh...
> We want you to build your vision for the Git platform of the agentic era using Cloudflare Workers and Artifacts.
> A link to the source code, which must be provided under a permissive open source license (MIT, Apache, BSD)
> We’ll select the top three projects and fly up to two members from each team to San Francisco to attend Cloudflare Connect and show what they built. The first-place team will also receive $25,000 in Cloudflare credits, along with invitations to the VIP speaker dinner on Monday night at Connect.
LOL. So basically they built some new product and it's not getting enough adoption. And they're looking to get (*almost) free labor to do the work for them.
> Deadline > October 14, 2026.
: .｡. o(≧▽≦)o .｡.:
but as others have said: $25k in credits as a reward for winning first place: this is not a real competition, this is just a minor marketing post so they get a few cheap clicks nwith no expectation of anything valuable from it
Cloudflare you silly goose, you ask an agent to review it duh.
Glad to see that my idea was on point, even though I ofc failed to make it into a competitive product.
Why all these additional complexity.
Yeah. No!
I like software built by humans who understand what the software does and can maintain it.
Maintenance is the ultimate boss!
Don’t want to use sloppy unmaintained over-complicated software.
They want us, external developers, to build it for $25k... But not cash. $25k of cloudflare hosting.
Why do I feel like it's the most insulting offer I have seen in a while?