If you were 5 microseconds late today, blame it on NIST.

Their facility in Boulder Colorado just had its power cut for multiple days. After a backup generator failed, their main ensemble clock lost track of UTC, or Universal Time Coordinated.

But even if you used the NTP timing servers they run, they were never off by more than 5 microseconds.

5 μs might seem insignificant. But it is significant for scientists and universities who rely on NIST's more specialized timing signals.

Ever since I got AMD, Intel, and Nvidia graphics cards to run on a Raspberry Pi, I had a nagging question:

What's the point?

The Raspberry Pi only has 1 lane of PCIe Gen 3 bandwidth available for a connection to an eGPU. That's not much. Especially considering a modern desktop has at least one slot with 16 lanes of PCIe Gen 5 bandwidth. That's 8 GT/s versus 512 GT/s. Not a fair fight.

Apple gave me access to this Mac Studio cluster to test RDMA over Thunderbolt, a new feature in macOS 26.2. The easiest way to test it is with Exo 1.0, an open source private AI clustering tool. RDMA lets the Macs all act like they have one giant pool of RAM, which speeds up things like massive AI models.

The stack of Macs I tested, with 1.5 TB of unified memory, costs just shy of $40,000, and if you're wondering, no I cannot justify spending that much money for this. Apple loaned the Mac Studios for testing. I also have to thank DeskPi for sending over the 4-post mini rack containing the cluster.

This little postage stamp is actually a full Raspberry Pi Zero 2, complete with eMMC storage and WiFi.

But you can't get one. Well, not unless you buy the CM0NANO development board from EDAtec, or you live in China.

This little guy doesn't have an HDMI port, Ethernet, or even USB. It's a special version of the 'Compute Module' line of boards. Little Raspberry Pi 'System on Modules' (SoMs), they're called.

Now that Nvidia GPUs run on the Raspberry Pi, I've been putting all the ones I own through their paces.

Many people have an older Nvidia card (like a 3060) laying around from an upgrade. So could a Pi be suitable for GPU-accelerated video transcoding, either standalone for conversion, or running something like Jellyfin for video library management and streaming?

That's what I set out to do, and the first step, besides getting the drivers and CUDA going (see blog post linked above), was to find a way to get a repeatable benchmark going.

Inside this Framework 13 laptop is a special mainboard developed by DeepComputing in collaboration with Framework. It has an 8-core RISC-V processor, the ESWIN 7702X—not your typical AMD, Intel, or even Arm SoC. The full laptop version I tested costs $1119 and gets you about the performance of a Raspberry Pi.

A Pi 4—the one that came out in 2019.

But unlike the Pi 4, this eats up 25 watts of power at idle, meaning the poor battery only lasts 2-3 hours.

Memory price inflation comes for us all, and if you're not affected yet, just wait.

I was building a new PC last month using some parts I had bought earlier this year. The 64 Gigabyte T-Create DDR5 memory kit I used cost $209 then. Today? The same kit costs $650!

Just in the past week, we found out Raspberry Pi's increasing their single board computer prices. Micron's killing the Crucial brand of RAM and storage devices completely, meaning there's gonna be one fewer consumer memory manufacturer. Samsung can't even buy RAM from themselves to build their own Smartphones, and small vendors like Libre Computer and Mono are seeing RAM prices double, triple, or even worse, and they're not even buying the latest RAM tech!

I finally upgraded to a mechanical keyboard. But because Apple's so protective of their Touch ID hardware, there aren't any mechanical keyboards with that feature built in.

But there is a way to hack it. It's incredibly wasteful, and takes a bit more patience than I think most people have, but you basically take an Apple Magic Keyboard with Touch ID, rip out the Touch ID, and install it in a 3D printed box, along with the keyboard's logic board.

A few months ago, GitHub user @yanghaku dropped a 15 line patch to fix GPU support for practically all AMD GPUs on the Raspberry Pi (and demoed a 3080 running on the Pi with a separate, unreleased patch). This week, GitHub user @mariobalanica dropped this (larger) patch which does the same for Nvidia GPUs!

I have a Raspberry Pi and an Nvidia graphics card—and I'm easily distracted. So I put down my testing of a GB10 system for a bit, and compiled mariobalanica's branch.

This air quality monitor costs $250. It's called the Air Lab, and I've been using it to measure the air in my car, home, studio, and a few events over the past few months. And in using it over the course of a road trip I learned to not run recirculate in my car quite as often—more on that later.

Networked Artifacts built in some personality:

Out of the box, if you buy a Raspberry Pi Compute Module 5, install it on the official CM5 IO Board, and install a fan on it (e.g. my current favorite, the EDAtec CM5 Active Cooler), you'll notice the fan ramps up to 100% speed after you shut down the Pi.

That's not fun, since at least for a couple of my CM5s, they are more often powered down than running, creating a slight cacophany!

I'm working on a more in-depth test of some newer AMD GPUs on the Raspberry Pi, now that the 15 line kernel patch is (IMO) nearly ready for upstreaming.

But this blog post shows how to quickly get almost any modern AMD GPU running on a Raspberry Pi 5, CM5, or Pi 500+, thanks to this patch on the Pi Linux fork.

Note: This patch actually enables AMD and Intel. I wrote about how to get Intel Arc GPUs running on the Pi yesterday.

We finally have Intel Arc GPUs working on the Pi somewhat stably—it required overcoming many small hurdles, but it looks like support could land in Raspberry Pi OS if we can get a simple patch upstreamed¹. If that happens, all you'd need to do to use an Intel card on a Pi is install a firmware package.

The cards I've spent the most time with so far are:

The Minisforum MS-R1 uses the same Cix CD8180 Arm SoC as the Orion O6 I reviewed earlier this year. But everything else about this thing is different.

What this thing should be, is a box that runs Linux and can compete with at least an Apple M1 Mac mini, or a mid-range Mini PC. But what we got... is something different.

Video

Hate reading? I also published a video on the MS-R1 on my YouTube channel. Watch it here, or scroll on past.

When you ground a hot dog to an AM radio tower, it generates plasma.

While the hot dog's flesh is getting vaporized, a tiny plasma arc moves the air around it back and forth. And because this tower is an AM tower, it uses Amplitude Modulation, where a transmitter changes the amplitude of a carrier wave up and down. Just like a speaker cone moving up and down, the plasma arc from the hot dog turns that modulation into audible sound.