> Compared to the $8,000 Framework Cluster I benchmarked last month, this cluster is about 4 times faster:

Slower. 4 times slower.

That's definitely a typo because I've to read the sentence 3 times from the article still cannot make a sense until I saw the figure.

TL;DR, just buy one framework desktop and it's better than the Pi AI cluster of the OP in every single performance metrics including cost, performance, efficiency, headache, etc.

Oops, fixed the typo! Thanks.

And regarding efficiency, in CPU-bound tasks, the Pi cluster is slightly more efficient. (Even A76 cores on a 16nm node still do well there, depending on the code being run).

But we are not talking about a malicious ssg, we are talking about a vulnerable ssg that somehow needs to be patched. Unless your ssg connects to the internet, this is a non issue.

> Unless your ssg connects to the internet, this is a non issue.

This, but for all software ever. In the nightmare realm we've apparently decided to settle down in we forgot the one way to make actually secure software: Run the complicated parts somewhere offline.

A security vulnerability is much less scary if the computer can't communicate with anything. It's the only way for us to get out of the pit of infinite work we've dug.

That doesnt help with CGNAT.

> I can't imagine how it would be possible to construct a jump call with an invalid value

You can use the bx instruction to jump to any address stored in a register.

> Additionally, what would happen if one of TheZZAZZGlitch's incorrectly reconstructed ROMs was run on a real GameBoy?

It would crash, and eventually start playing the ROM on the speaker, the whole point of the video :)

Thanks for the explanation! So it sounds like the emulator is detecting the error 'out of band' with the emulated execution flow, and choosing to throw an error message rather than letting the execution continue. If it didn't catch the error, it sounds like it would glitch out in much the same way as the real GameBoy would. Is that right?

That's right. This sort of thing is more likely to indicate a discrepancy between the emulator and the real hardware, than actual game behaviour, so emulator developers choose to treat it like a crash. Some emulators have "continue anyway" buttons and some don't.

For x1.5 the price, from what I can see. Are there any under $100?

No but with the raspberry you're not there without a power supply, case, cooling and storage.

Add them up and a Quad-Core N100 becomes equivalent. Here they're on Amazon for 180€ with 16GB ram and 512 GB storage. And cheaper options with less storage and ram (usually coupled with the sightly slower N95 chip)

It's not a pi and if you want to integrate it into electronics a pi is much better but for the "small mini server" usecase I don't see the benefit of going for a pi anymore.

We were comparing the N100s not to the Pi5 but to this $98 Wo-We AMD: https://www.wo-we.com/collections/mini-pc/products/mini-pc-a...

The grandparent comment said you could get an N100 for the same price, but they are all more expensive no matter how you look at it.

Oops I overlooked that discussion, sorry.

That is sure a nice system for the money! Wow. I will check if I can get those in Europe.

The typical modern gaming PC uses a lot more power than the original xbox. Yes maybe it's more efficient because it's doing "more", but in the end it's one person playing a game.

Depending on what you are patching, it will invalidate a great part of the cache, and you will be looking at very long build times for everything in your system.

If that dependency is deep in your dep tree and is statically linked somewhere than there is no way preventing that.

If it’s only dynamic linking than yeah, it might happen that you need a huge recompile (but that is not that big of a problem nowadays in my experience - gentoo used to compile way longer in my subjective experience for example). Also note: nix will soon get content-based hashing which may solve this problem.

For that reason many modules have options to set the packages used, so that you can eg. patch openssh without rebuilding everyone.

I gave up scrolling the terms and conditions.

Oh, I hadn't even seen that. You don't need to open them up. just uncheck the checkbox.

The CAPTCHA at the end was my favorite part.

Because you missed this line:

> Holding ALT to scroll faster is cheating and not allowed.

or wilfully decided to not cheat.

But not every synesthetic person sees the same colors for every key, right?

I have a step in my fashion work where I pause and consider what the colors I’m selecting will look and feel like to a normal person. Converting back and forth between [optimistic-seaglass-springtime] and “teal” isn’t very accurate, but I’m certainly accustomed to it. I’m going to try this technique soon now that I know about it; as I’m already color sensitive to pitch, I suspect the value will be in training that sensitivity rather than memorizing their hues.

Is it possible to fall back to a jpeg if the browser does not support js, wasm, or web workers? With a <picture> element, maybe?

I did some tests on my own server and found that for some reason it's quite fast when running on https, but super slow on insecure http. Not sure why that is, maybe the browser disallows something that's important here for insecure connections.

Yes, you can use <picture> to fall back to JPEG/PNG/WebP.

https://cosarara.me/misc/jxljs/ in my test, it will simply fall back to jpeg, even if the jxl.js library is loaded (scroll down to Image with fallback).

This is because JXL.js doesn't support `<picture>` tags - there is no rationale for WASM-decoding JXL when you can provide a fallback in natively-decoded JPEG/PNG/WebP.

The rationale would be that it might be more efficient to WASM-decode JXL than to download a JPEG, especially in pages with lots of images, but I would want a fallback if the browser does not support WASM.