May 16, 2026, 1:36 PMMy first job was building out the first mega-datacenters. 2005-2007, I was a datacenter assistant monkey working from Google working somewhere in the Chicago suburbs, swapping out hard drives and ram and writing shell scripts, as myself and my friends unknowingly laid down the prototype for the kinds of datacenters we all see today.
And so it is with some significant expertise that I say:
Fuck datacenters. Datacenters are an anti-pattern.
May 16, 2026, 1:40 PMWorking in that environment, seeing as Google rolled out the idea of "cloud computing" meaning "you have no involvement or agency in your computing because we do it for you" radicalized me for much of the work of my career.
It was one thing to run a datacenter to index the world's public web information. I understood that, it made sense.
But watching as Google and Apple co-developed the idea that computers, which I cared about, got abstracted into toys and jewelry that had all your key computing done in a way you had no agency over... where I saw firsthand the kinds of churn of resources necessary to keep these things going, it made me want to fight for a different computing future.
@cwebber that's an interesting point of view. I mean, of course the current datacenter craze is complete madness, but it seems you consider an anti-pattern the concept of datacenter itself. Why is it so? What do you suggest as an alternate solution to the problems data centers try to solve?
May 16, 2026, 1:41 PM@farfalk Datacenters are concentrations of power. Anytime a datacenter is involved, it's a sign of power centralization. The rise of datacenters corresponds with the death of p2p and other visions of a more decentralized internet.
@cwebber @farfalk I think it more corresponds to the death of personal computing as it was? People don't have desktops anymore and barely have laptops other than for work? Which is a problem for p2p? Seems like most people's decentralized/federated nodes for things are hosted in data centers? All question marks because just speculating.
May 16, 2026, 4:01 PM
@cwebber @farfalk like, I can appreciate some of the advantages of having them. Like you could get more computer per watt, maybe. I think valuable research is done with supercomputers and modern, more modular approaches to big data. But we could do way more with way fewer datacenters if these weren't used as a way to paywall functionality at the server side. The move to the cloud almost makes me miss when my problem was Cubase requiring a USB dongle.
@thomasjwebb @cwebber @farfalk there is always a "but sometimes" so maybe we can take it as a given that for any strident statement in short form chat there isn't all the nuance about exceptions.
The overall direction seems right to me though. We've got a not insignificant ipv6 deployment for residential use, where is the Cobalt Qube of personal computing? There is no good *technical* reason I shouldn't be able to host my personal email on my own domain, at home, on my own computer, along with a website or whatever. Big monopolistic platforms, which require huge datacenters and complex tech stacks, are an antipattern.
@raven667 @cwebber @farfalk sure I just don’t want to be seen as someone who hasn’t considered the obvious counterpoints. I have the “always include depth-first nuance” kind of autism and ocd. But yeah I think if we design protocols right, maybe people won’t even have to self-host in many cases. It could be some truly p2p stuff than can run on the client.
@thomasjwebb @raven667 @cwebber @farfalk exactly! where we're going we don't need websites, we must abandon the concepts that require single-point-of-failure "hosting" because that is not viable in a local-first world.
May 16, 2026, 3:05 PM@farfalk @cwebber Really look at “the problems data centers try to solve”. At face value, LLMs and other “AI” are not functional or even profitable by themselves, but they are the supposed reason for the data center boom. But there’s strong evidence that the boom is driven by market manipulation for the hardware, not organic demand for its work. Further, the face value function of “AI” is to extract short term cash value while denying resources to humans. That is the secondary problem the centers try to solve (first being fraudulent investment in the centers themselves). That’s why framing it as “what’s your alternative” is a mistake.
@Moss @farfalk @cwebber sorry I can't quite understand your point. I am sure you use the internet for distributed software; data centers per se allow networking. Having products controlled by monopolistic rent seeking companies that haven't a better business plan than ads is a political problem, not so different from rail roads/oil distribution; political solutions will work when we focus on democratic power not individual purity. Bubbles happen when $ is unregulated by work/life/democracy.
May 16, 2026, 5:54 PM@jayalane @farfalk @cwebber “data centers = networking” is the same as saying “data center water and power consumption = indoor plumbing and wiring.” We had global networking long before the present eruption of resource-hogging new data centers. My point was exactly as stated: the so-called problems that the DCs are supposed to solve are fake. A narrative beard for fraud and global resource extraction.
What do you suggest as an alternate solution to the problems data centers try to solve?What actual problems do data centers inherently solve to begin with?
May 18, 2026, 11:41 PMMay 19, 2026, 11:13 AM@cwebber do you have a writeup expanding on “datacenters are an anti-pattern” because this is 100% how I feel. I’m not fighting over AI. I’m still fighting over the cloud. Society has badly fumbled the fact that everyone has incredible computing power in their pocket. We’ve already been wasting electricity on idle servers and inefficient high level code. I’ve been - and am - part of the problem, moving functionality to the cloud for business reasons I hate.
May 16, 2026, 1:56 PM@thomasjwebb I've been meaning to write a blogpost for a long time. Sounds like it's time to write it!
@cwebber @thomasjwebb I remember "datacenter" starting as "colocation hoster" - you rentet rackspace or several racks with redundant power supply, internet link, packed in some pizzaboxes and a router, and there you go. Physical safety was better than the rack with dev servers in the basement, so what else could you ask for?
@Reinald @thomasjwebb @cwebber colocation of your own stuff is ok
@mirabilos @Reinald @thomasjwebb @cwebber apparently not. Most of the people in these threads seem never to have heard of a data centre before last year. I’ve been hosting stuff in them since 1994 at least. At that point they were mostly for telecoms gear.
Though I’ve almost never done the cloud compute thing.
May 17, 2026, 11:49 AM@Colman @mirabilos @Reinald @thomasjwebb Yeah, we are far from those days for the most part. I'm very familiar with those. But most datacenter deployments aren't like that anymore.
@cwebber @Colman @mirabilos @Reinald @thomasjwebb may I ask, how would you describe the change between then and now? I've never been in a DC and want to better understand when centralization turns noxious
@xlrobot
Let me try: I see 3 major facors:
Uniform scaling
Energy density
Cooling requirements
Colocation was wild - you rented Rackspace, and had the "remote hands" move your gear in. Everybody was using different makes. Storage servers, Compute Power, maybe some Backup Tape Library, A router. A full Rack had 6 to 8KW of power consumption.
Our webhosting DC had about a Dozen Racks in a room with wooden office doors, cooling was a monoblock AC.
Please do!
@cwebber @thomasjwebb
May 17, 2026, 12:02 PM@cwebber this resonates strongly with me. I first got "on the internet" in ~ 1994 as a student, when I got the PC in my room hooked up to the college ethernet. I could run the cern httpd and publish my own web pages! I could telnet to my room from labs! I could write a C program that opened a listening socket, and anyone on the internet could connect! I could finger myself! (That sounds more wrong now than it did then). Notwithstanding that my bandwidth was limited to whatever a 3c509 could provide (which, actually, was plenty back then) I was an equal participant in the internet. My computer was a peer.
A couple of years later I started seeing jobs in this new and exciting sphere of "putting stuff on the web", and the picture had changed. No longer "we will hook you up to the internet" but "we will host the pages we create for you on our own server, and there are barriers to your access to changing them". It had gone asymmetric. I concede there were sound practical reasons (cost, security, support) for doing it like that, but that's when the magic started to leach out.
May 17, 2026, 12:06 PM@cwebber my grandfather was a pharmacologist, and an early adopter of microcomputers in the 1980s, because he wanted to use computers without jumping through the hoops that governed access to the institutional facilities (which I assume were batch or timesharing) at his university. I remember waxing lyrical about the internet to him in the 90s and his reaction was "it sounds just like the terminals we were trying to get away from". I thought at the time he'd missed the point completely, but 30 years down the line and it seems more like he was prescient
@dan @cwebber and the thing is, it COULD have been done differently. The centralising models were the strongest attractor in the *short term* because they fitted a VC-funded growth economy in a time where dialup was still common, so got lots of investment, but we could also have developed the culture towards commodity router+server devices with easy to use software to set up local hosting as easily as installing smartphone apps. And we still can...
@cwebber The appliance-ization of computing really depresses and infuriates me.
Growing up with early personal computers in the 80s, the magic and the promise was you could use these machines to do *anything*, including things nobody else thought or cared to do!
A big part of what I fought to build in Android was a mobile platform that'd also deliver on the "you can run anything you want" promise of the machines I grew up with... sadly over the past decade that has been seriously eroded.
@cwebber Very mixed feelings about the ten years of my life I spent building a platform that managed to be both wildly successful beyond anything I could imagine (especially relative to Hiptop/Sidekick, my first time building one from scratch), and also that seriously failed in some was both predictable and not.
My hope is it's getting more possible to build something like that without doing so under the umbrella of some enormous corporation, and maybe there will be a chance to try again.
May 18, 2026, 11:48 PM@synec @cwebber Yeah, it certainly could have been a lot worse. One area I wish I had gotten more involved in was the SDK side of things. App development for Android is such an absolute nightmare. There weren't enough hours in the day to fight all the battles, sadly.
And I think you end up with a limit on the number of credible threats to quit over stupid management decisions (number three for me involved actually starting to pack up my office on a weekend before being talked into staying).
@swetland @synec @cwebber I came here to say this. I've done some (small amount of) Android firmware development, which is more than Android app development, because it is literally easier to work on the system components than figure out what combination of Maven, Kotlin, and goddess knows what else Google expects you to develop in today
@whitequark @synec @cwebber Yeah, the only app development I could ever deal with was building apps as part of the system build. Even in the early days the public SDK stuff was crazy clunky and it just keeps getting more horrific.
I also really regret never managing to get a "no you don't need any java or any other cruft" model for pure native apps put together (early on it was political, later java was so entrenched in the library interfaces it became an impossible battle to win).
May 19, 2026, 1:46 AM@whitequark @swetland @synec @cwebber just switched over the calibration system for our telescope from an android phone with an OLED to an FPGA driving a DLP because the latter is much easier to program
May 19, 2026, 1:49 AM@whitequark @swetland @synec @cwebber I could not figure out for the life of me how to convince the phone that yes I really did want to be full screen and yes I really do want the brightness and refresh rate to be locked from a native app
May 19, 2026, 1:52 AM@whitequark @swetland @synec @cwebber (that said not even sure it's actually possible to build an application in IOS)
May 19, 2026, 1:58 AM@whitequark @swetland @synec @cwebber that was my initial plan yeah, it was ancient galaxy, so I updated it to the last version of lineageOS that supported it so I could load a version of Firefox that supported WASM +WebGL
Due to some rules I don't remember off the top of my head you can't have a full screen website bookmark unless the website is served over https in Firefox iirc and it can't be connected to the internet
May 19, 2026, 2:02 AM@whitequark @swetland @synec @cwebber oh that's handy I did not know that
May 19, 2026, 2:13 AM@whitequark @swetland @synec @cwebber wait who will sign those?
@swetland @cwebber
Don't beat yourself up too much. It's mostly Apple that's responsible for fucking up general-purpose computing, but once they started down that path, all major competitors were forced to follow. The decision to do that is by management, not engineering.
Seeing Apple do that, after I'd been a dyed-in-the-wool, bleeds-in-six-colors Apple fan since 1977, made me feel sick.
May 16, 2026, 1:50 PM@cwebber even the ones where they rent rack space to specific customers who own their hardware and physically come to the premise to maintain their own stuff? I think those are okay and _better_ than hosting things at home.
May 16, 2026, 1:54 PM@cwebber and yes then you have a datacenter landlord so arguably still a concentration of power, but a manageable and acceptable level IMO.
I spent half my career maintaining plastics manufacturing plants. I learned about what effects that had on the environment, so I started maintaining food production plants. Yeah, highly processed foods. So, I'm now working with very low energy electronics. Hopefully, a few electrons might be less damaging to our future...
@cwebber @YakyuNightOwl Looking at the replies, I'm seeing so many of us who built this who are in dismay at what it was built into.
For me it was working for an enterprise CRM/CIM software company '05-10. I supported the development of knowledge bases and customer support streamlining (chat, automation) because I thought it would be used to relieve call center agents and help customers get to accurate information faster. Instead it became a dehumanization tool, distancing customers from accessing real people and real help when they actually need it, and reducing the tech skills of agents. Utterly devastating.
@cwebber
huh
interesting.
about that same time;
had 3 interviews with the goog
as a 'linux beige box wrangler'
at a big campus dc in northern va
my linux clue-kit was deep & shallow at the same time
they passed me over
I was bummed, bigly
then it all changed
May 17, 2026, 12:10 AMI worked in a data center from 2002-2013, moving from an infosec role to sysadmin halfway through (so more and more down among the racks as time went on).
This particular datacenter was built in the late 70s, under the rule of "old I.T./Data Processing," where guys would come in at 8, grab a cup of coffee, grab a stack of greenbar printouts, and spend a couple hours going over reports before really starting the day. The laid-back atmosphere lasted until the late-mid 2000s, when the company got sold, we all got outsourced to a TLA, and it turned into (relatively speaking) a living hell. (Probably paradise compared to today's I.T., though).
The actual computer rooms were all in the basement, so all you saw above-ground was offices/cubicles.
I had dreams about deep, dark foreboding computer basements for years after leaving I.T. 😂
I cannot imagine what modern datacenters must be like.
If things progress the way they are, I can see datacenter terrorism (e.g. Molotov Cocktails and such) being a real thing. Just imagine people seeing their children not able to access potable water while Giga Mechanical Turk* down the streets sucks down the municipal water supply while belching pollutants and screeching noise.
I wanted the future to be Star Trek, not Cyberpunk, dammit.
I'm incensed that the modern computing needs of the average person could be handily served by a $100 junk PC, but now we have to build planet-destroying industrial data centers to serve up stochastic smalltalk. Freaking heck.
* Referring to a historical fake-automaton, not an epithet against Turkic people, of whom I (partially) am one.
cc: @mirabilos
@rl_dane @cwebber @mirabilos Here's a completely unrelated bit of history.
May 17, 2026, 12:24 AM@foolishowl @cwebber @mirabilos
I'd love to see I.T. workers with that much gumption. 😢
I cannot imagine what modern datacenters must be like.
Cold, and loud enough you’d need ear protection by law, at least in the actual server rooms. Artificial lighting only, of course, even if it’s above-ground. And security to fear, even if [sometimes duck-tried (Thread)].
That’s modern as in before 2019.
May 17, 2026, 1:16 AMHoly crap, that was a treasure 🤣