Hacker News

Oxide certainly sounds cool. It reminds me of when I dealt with DEC gear back in the late 90s. That stuff felt more like "real computers" than any of the IBM PC-derived drek I'd worked with. Things were actually made to work together. Configurations were tested. Firmware was made for the integrated system and the system behaved like it was meant to work together instead of being the manifest behavior of all the edge cases of all the off-the-shelf disparate components plugged-together to make the resultant machine.

I don't need to work there (nor do I feel like I'm smart or talented enough to)-- I just wish I could work with the Oxide gear in Customer engagement, too. I don't work with businesses big enough to need it, sadly. It looks so sweet.

This is what I think of when I think of utility-scale compute-- not racks of Supermicro / Dell / HP boxes with tiny ISA buses hiding on traces on their motherboards for "baseboard management controllers" to plug into to pretend to be PC AT keyboards.

Oxide is literally the only company where I have found zero reasons why I would be unhappy to work there. I have listened to many, many podcasts, read RFDs… it always seems like a place I would thrive. To that end, I have applied twice in the last few years; unfortunately declined both times, but to be fair, the first time I didn’t know any Rust, and the second time, I was learning it.

I will apply again at some point when an interesting job comes up, and I have a stronger skillset.

I'm pretty sure I'm not talented enough for Oxide, but just asking myself the application questions has been a fun exercise. I'm not in love with their problem space, but I am really into the way they work and do business.

Greatest hope: their approach catches on outside just Oxide, and I get to work somewhere with a similar ethos and practises one day.

Greatest fear: the way they work only makes sense for the most elite and well-capitalised of companies.

There are two companies that I want want to work for. Oxide is one of them. Many places I'm still willing to work for, but in a more neutral way. They're just mostly not hiring for my role/location as far as I can tell, so it is what it is.

Just a gentle reminder that a company may portray itself as cool to customers, but is not cool to their own current or future employees.

Their interview process was shady. There was a post here about 1-2 years ago that was a link to their interview process and how open and transparent they were. The post itself was from an employee and a fellow commenter who was gaslighting folks was also an employee. Several folks complained about the tremendous amount of homework they had to do after the initial screen, and once submitted, were ghosted. One of employees repeatedly rebutted that claim in the comments, and they did this for quite a few commenters. Was a not a good look. I doubt much has improved since then as seeing the comments below confirms the same mess.

Don't spend time being amazed by folks who won't treat you right. It just ain't worth it.

Thought of the same, has a big Sun Microsystems vibe.

I've gone through the same process, not so much that I don't think I would be worth considering, but serious code and documentation examples aren't something I can really give out given that they're proprietary. this last winter I started a whole guest-kernel based syscall intermediation and distribution framework in rust just for the application. with all kinds of design documents. I was about 30% finished by the time I landed a job somewhere else :)

but I still applaud the intent. I self-selected out by giving into scope creep

Many years ago, I quit the technology industry because I thought a company like Oxide could never exist. I want to work for them but I'm not sure I'm qualified. Maybe one day I'll apply.

Oxide is the only company I can think of that carries the torch of what silicon valley used to be in the 90s. Actual, awesome, cool technology! I wish massive success to Oxide.

Seriously - looks so cool

> Somehow hardware giants like Dell, HP, SuperMicro, etc didn't make a product like this, even at their peak in 2000s or during cloud boom in 2010s.

Not so sure about this one. HCI (Hyperconverged) rack units (where storage and compute live in the same racked systems) and "blade servers" have been a thing for a really long time now; compute sleds aren't what's novel here.

Rack-level DC conversion is also not particularly novel, although underutilized IMO. It was pretty popular in HPC style density applications for awhile (see HP/SGI Altix 4000 for a good old example).

What's unique about Oxide is that they went all the way down to the firmware and then back up, rather than doing commodity hardware integration or reselling - for example, you can get something like a Supermicro EVO:Rail, but it will be running VMWare, not a fully integrated platform.

The big difference that everyone is missing in this subthread is that Oxide is about the hardware and the software.

There are systems which have similar overall hardware designs, but they are usually integrating a large amount of hardware and software from multiple vendors. Oxide is much closer to "everything is produced by Oxide."

I wrote this back in 2022, and it's still fundamentally relevant today: https://news.ycombinator.com/item?id=30678324

I wish I could edit my post.

Somehow everyone wrote to me about baldes. These are not the same, though. Blade servers were mounded into units of 4u, 8u, etc, they occupied a portion of the overall cabinet and still had to do "plumbing" for power and networking behind the chassis to the rest of the cabinet or to the rest of the datacenter. A full-cabinet blade rig would have multiple 8u blade units and some off the shelf units for networking, storage, etc. Yes, you could mix and match different components based on your needs, but that also meant that there were extra wires, cables, mounting rails, and more importantly - all these different components ran a mix of software that had to integrate using common denominator protocols and speeds.

Steve rightly mentioned the integration below, and I didn't put it in my message because I kinda assumed that we include software in this discussion too.

HP in 2005 had an army of programmers writing all sorts of firmware and software and another army of hardware engineers, too. They could have made an Oxide computer back then, and it would sell really well. But they didn't, and none of their competitors did despite this being an obvious product (in hindsight), an THIS is what I find interesting.

> Somehow hardware giants like Dell, HP, SuperMicro, etc didn't make a product like this,

Dell and HP both have "blades" that plugged into a blade-chassis. The chassis had all the lights out mgmt as well as power/networking integrated so the blade was basically a metal box with compute/memory/storage and it just slid in to the dock.

I am sure that supermico had something like this as well

Meanwhile a Hetzner rack: https://i.redd.it/u3o410rwdt6h1.jpeg

Blade servers have been doing this for 25+ years.

The vendors did make blades in the 2000s.

> Somehow hardware giants like Dell, HP, SuperMicro, etc didn't make a product like this, even at their peak in 2000s or during cloud boom in 2010s. I wonder why?

They all did. HP had Super Dome and blades and Synergy. Dell had similar.

I learned about blade servers back in ~2010 because Blizzard used to run World of Warcraft realms on them and auctioned them off for charity.

https://warcraft.wiki.gg/wiki/Server_blade

https://en.wikipedia.org/wiki/Blade_server

Oxide's sleds don't conform to U sizes directly, IIRC. And even though I'm not there anymore, I can say for sure that it's not going to shrink to 1U: the larger size is very important for other reasons. For example, the larger sled size means larger fans, which means that they can be run at lower speeds, meaning less power draw, less wear and tear, and less noise.

> water cooling only.

There's some comments above about water cooling, I doubt this will happen, but we'll see I guess.

Wouldn't that person want to have everything work well together so he has less headaches?

You don't need oxide, you can't afford it, and you're not a target customer.

All we can say is empirically this is not true. Plenty of people whose full time job is managing rack infra are sick and tired of the customizability of commodity hardware, of the many custom bugs in commodity software, and of the customizability of the price of VMware.

Thanks for sharing that. Very cool - was this sales product that you decided to release or has it always been public?

Thank you for rooting for us! One important point of clarification: I am the CTO -- the CEO of Oxide is my co-founder, Steve Tuck. Long before we know what we wanted to do (or had a name for the company!), Steve and I knew we wanted to do something together; it's worth getting to know Steve (and our collaboration) in his own words![0][1]

[0] https://www.youtube.com/watch?v=eVkIKm9pkPY

[1] https://www.youtube.com/watch?v=d_XqNYt0cY0

Hard to compete there when most of the margin is going to NVIDIA, pretty much impossible if you don't have the scale of Dell/Supermicro/etc

The sleds blind mate to power and network on the backplane so removing the sled will disconnect it. Once the sled is disconnected you pull the fan assembly out and replace it.

Any console errors? Perhaps drop an issue on the repo if you have a moment: https://github.com/oxidecomputer/rack-explorer/issues

That's why I prefer BSD :P

completely locked my machine up with Firefox on Linux. Gave up after that.

https://news.ycombinator.com/item?id=48677980

I'm sure you're aware there's a huge amount of computation that isn't matrix multiplication :)

They didn't. They actually said they have huge demand because of AI companies. Turns out, when the AI is surfing the web or using doing other task, that's a CPU. So they also have demand for CPU.

Not worth the capex to do that. Air cooling with evaporators up front is pretty standard and works great, not to mention fewer moving parts.

99% of data centers do not have liquid available to the rack. Liquid within the rack doesn't really help.

I don’t think there’s a GPU component so it’s probably a much lower power profile. Also, per this cloudflare write up the Turin gen of the AMD Epycs is very efficient: https://blog.cloudflare.com/gen13-launch/

Interop standards for this like Open19 are not widely deployed and without interoperability it’s a dead end since you need the hosting provider to give you the drop to your rack or cage. Hyperscalers I don’t know, but I’d guess they don’t deploy rack density that calls for liquid cooling yet.

IIRC the CAD exports were in the many millions of polygons, so there's substantial work in preparing the assets for the explorer. Kenan (the 3d artist I worked with) did fantastic work cleaning and optimising them. I'm somewhat jealous of hardware startups with products without quite so many parts!

It's part of the reason I'd waited so long before making this, I knew it was going to be a lot of work. There's parts that Claude was especially useful for, like perf testing, debugging and animation. But the first half of the project was done almost entirely by hand.

My feeling? I ask myself the same question as I do for for everything nowadays. Yeah this might be ai slop, but is it good ai slop? If it's good, like this, I feel good. If it's bad, I feel bad.

Human effort as a proxy for quality... that ship has sailed. And that makes me feel frustrated.

Absolutely

Yes. I believe the first public post about a customer was this one, in 2024: https://oxide.computer/blog/oxide-computer-company-and-lawre...

https://news.ycombinator.com/item?id=42721998

Agreed. Oxide, TigerBeetle and Zig.

IIRC I heard that a single rack is upwards of $600k–$1m, but that was before the AI boom/crisis.

With only 288 128GiB DDR5 ECC DIMMs? I'm sure that doesn't cost much.