Deep Dive into the Gateway API Inference Extension
Running AI inference workloads on Kubernetes has some unique characteristics and challenges, and the Gateway API Inference Extension project aims to solve some of those challenges. I recently wrote about these new capabilities in the kgateway… ⌘ Read more

golf.vim v0.1.1 - fixed keystroke logging, removed ultra‑short runs, now captures all modes ⌘ Read more

@prologic@twtxt.net Hmm, speaking of locally running “AI” stuff: Someone on Mastodon has this in their profile description:

My profile pic is AI modified to prevent deepfakes. I used local Stable Diffusion on my solar powered 7900XTX to average a few selfies.

That sounds like a fun thing to do. Do I have a chance of doing that on my old box from 2013 without a dedicated GPU? 😂

There are other tasks LLM(s) are far better suited for, which are also its downsides, and gawd so expensive and unrealistic to run yourself 🤦‍♂️ Do you know what one of these NVIDIA H100’s cost? 💲 That’s right! 🤣 > $50k USD 😱 And many of the models out there require 8 of these suckers 🤣 Each one consumes around ~400W of power each (not including the machine that houses them!)

Pinellas County - Long run: 11.28 miles, 00:10:03 average pace, 01:53:15 duration
was suppose to get 20 miles today but after working outside nearly the entire day i was worn out and called it early.
#running

@kate@yarn.girlonthemoon.xyz I already have my IRC server irc.mills.io running behind Caddy Layer 4. However I don’t terminate TLS at the edge in this case.

it is infininately simpler to run/operate 🤣

@bmallred@staystrong.run I don’t use it, it is @movq@www.uninformativ.de the one who does.

@kat@yarn.girlonthemoon.xyz is there anything i can even run or is this like email where you should just use libera and shut up

That was a wild ride:

https://www.youtube.com/watch?v=QSMDb1CWD6Y

Notice how old all these people sound. They started playing this game like 10, 15, 20 years ago, most of them left, but some are still there. I love that level of commitment. 😃

Also interesting from a technical point of view. Creating that virtual world and keeping it running consistently for so long … 🤯

@prologic@twtxt.net @bmallred@staystrong.run Ah, I just found this, didn’t see it before:

https://restic.net/#compatibility

So, yeah, they do use semver and, yes, they’re not at 1.0.0 yet, so things might break on the next restic update … but they “promise” to not break things too lightheartedly. Hm, well. 😅 Probably doesn’t make a big difference (they don’t say “don’t use this software until we reach 1.0.0”).

Pinellas County - 5 miles: 5.00 miles, 00:08:21 average pace, 00:41:46 duration

#running

@prologic@twtxt.net @bmallred@staystrong.run So is restic considered stable by now? “Stable” as in “stable data format”, like a future version will still be able to retrieve my current backups. I mean, it’s at version “0.18”, but they don’t specify which versioning scheme they use.

@kat@yarn.girlonthemoon.xyz lack of RAM, or weak CPU? I run GoToSocial too, on a 1GiB RAM VPS. 😅

CAN MY FEDI INSTANCE STOP CRASHING

(it is running gotosocial which is like one of the lightest fedi servers out there. the machine it runs on is as old as a high schooler. guess the root problem)

Running - 5 miles: 5.50 miles, 00:08:15 average pace, 00:45:23 duration
got a bit carried away with the music
#running #treadmill

What makes Slackware different?
I’m not entirely sure how to link to this properly, but what we have here is a simple, to-the-point text file describing some of the benefits of Slackware, the oldest still maintained Linux distribution. It’s still run by Patrick Volkerding, and focuses on conservative choices and simplicity over ease. I doubt I have to explain the benefits of Slackware to the average OSNews reader, but this simple little text file does serve as a great marketing tool. The fact it’s a … ⌘ Read more

MacOS Sequoia 15.4.1 Update Released with Bug & Security Fixes
Apple has released MacOS Sequoia 15.4.1 as a software update for Mac users running the Sequoia operating system. The update focuses exclusively on security updates and bug fixes, and contains no new features. Separately, Apple also released iOS 18.4.1 for iPhone, iPadOS 18.4.1 for iPad, and updates to tvOS, watchOS, and visionOS, and those updates … [Read More](https://osxdaily.com/2025/04/16/macos-sequoia-15- … ⌘ Read more

Pinellas County Running - 8 miles: 8.09 miles, 00:09:00 average pace, 01:12:47 duration
another great run although i know i was going a bit hard
#running

Whiskey developer throws in the towel, suggests to just buy CrossOver instead
Isaac Marovitz, the developer of Whiskey, a frontend for Apple’s Game Porting Toolkit and Wine, has decided to throw in the towel. The developer is advising users to buy CrossOver instead, which provides the same service. The reasoning behind their decision seems sound, and are actually quite noble and considerate. First and foremost, it’s the usual problem lone developers run i … ⌘ Read more

Pinellas County - 5 miles: 5.02 miles, 00:08:36 average pace, 00:43:07 duration
amazeballs
#running

Five Critical Shifts for Cloud Native at a Crossroads
As enterprises run ever-more-complex workloads on Kubernetes, they’re facing a new set of challenges: how to ensure security requirements are met, budgets are deployed efficiently and operational complexity is, well, not as complex. Many are finding… ⌘ Read more

@lyse@lyse.isobeef.org do you run your own Jabber server, or piggy back on someone else’s?

@bmallred@staystrong.run I just realized I was only suppose to do 5 miles at pace and not 8.

Pinellas County - Long run: 12.03 miles, 00:09:11 average pace, 01:50:36 duration
schedule called for 12 and it got it. again felt light today… almost an all-day pace but just slightly faster. i hope i am not peaking too soon.
#running

@prologic@twtxt.net you wrote:

“Based on a recent study of the brains of mice I estimated the human brain to have 200B cells/neurons and 50,000T connections.”

What’s the relation between the brains of mice, and the human brain? I am kind of lost trying to make the connection.

I also read that it isn’t 5 watts, but more like 10-20 watts. Still a super tiny consumption, comparing to what it takes to run anything AI.

“Move to iOS” app continuously refused to run as intended and expected, so couldn’t migrate mum’s Android based phone data. Most of her stuff is on a Google account, but not the SMS/MMS/RCS messages. Haven’t found a way to export, then import those into iOS.

She isn’t too happy having to keep the old phone just for the messages. Need to find a way to go through them, export multimedia attachments, and import them into iOS. I don’t think it’s going to happen, but I am not letting her know yet. 😅

Pinellas County - 8 miles: 8.01 miles, 00:08:43 average pace, 01:09:49 duration
felt so light today (minus the last hill) but i knew i was probably going a bit too fast for the workout.
#running

Add support for skipping backup if data is unchagned · 0cf9514e9e - backup-docker-volumes - Mills 👈 I just discovered today, when running backups, that this commit is why my backups stopped working for the last 4 months. It wasn’t that I was forgetting to do them every month, I broke the fucking tool 🤣 Fuck 🤦‍♂️

When you’re four weeks old but already running a spa. ⌘ Read more

How to Run DeepSeek LLM Locally on Mac
If you follow AI news, or even tech news, you might have heard of DeepSeek by now, the powerful Chinese Large Language Model that has capabilities rivaling ChatGPT while having dramatically lower training costs. DeepSeek is designed for advanced reasoning, with general purpose natural language and ChatBot abilities, task competency, research, while also being excellent … Read More ⌘ Read more

5 miles: 5.00 miles, 00:09:06 average pace, 00:45:32 duration
mandatory easy again
#running #treadmill

What’s up with Linux support for Qualcomm X Elite chips?
Remember when Qualcomm promised Linux would be a first-tier platform alongside Windows for its Snapdragon X Elite, almost a year ago now? Well, the Snapdragon X laptop have been out in the market for a while running Windows, but Linux support is still a complete crapshoot, despite the lofty promises by Qualcomm. Tuxedo, a European Linux OEM who promised to ship a Snapdragon X laptop running Linux, has posted an update on … ⌘ Read more

oh out of boredom yesterday i made my blog available via markdown files too so you can use charmbracelet/glow to read them in your terminal :)

basically i just set up a file directory on a path of my blog, organized the MD files by year, and so in theory you can navigate to that path and choose a folder, then copy a link to a markdown post and run this:

glow -p https://bubblegum.girlonthemoon.xyz/md/2025/2025-03-31%20premature%20reflections%20on%20sudden%20responsibility.md

and then as long as you have glow installed, you can read my posts from the terminal :D it’s so cool

guys omg the people behind pico.sh are so nice ;_; one of the people running it emailed me to let me know i had what was likely a malfunctioning (or well, not working as intended) script that was spawning the same SSH tunnel over and over and they wanted to give me a heads up.

and i felt SO BAD because i worried i was straining their service or something so i disabled my 4 tunnels (they were serving little SSH games and services) and got back to them.

but i just woke up to THE NICEST EMAIL EVER reassuring me that i was actually using it as intended, it was just my script that was having problems, and they even said that if it was intended to work that way it was fine and they just wanted to let me know!

so i restarted the tunnels but have since added lockfiles as safeguards so that when the script is run it’ll check if it’s already running :D

5 miles: 5.00 miles, 00:09:23 average pace, 00:46:57 duration
treadmill today to make sure i keep it easy
#running #treadmill

Run Gemma 3 with Docker Model Runner: Fully Local GenAI Developer Experience
Explore how to run Gemma 3 models locally using Docker Model Runner, alongside a Comment Processing System as a practical case study. ⌘ Read more

Introducing Docker Model Runner: A Better Way to Build and Run GenAI Models Locally
Docker Model Runner is a faster, simpler way to run and test AI models locally, right from your existing workflow. ⌘ Read more

Kubernetes hardening made easy: Running CIS Benchmarks with kube-bench
In today’s world, where security risks and breaches are growing daily, it is crucial to maintain our applications and infrastructure’s compliance with security standards and that is where CIS benchmarks from CIS (Center for Internet Security)… ⌘ Read more

Pinellas County - 5 miles: 5.00 miles, 00:08:59 average pace, 00:44:54 duration
it was good to run through the park again. had to make a pitstop but the run felt pretty strong.
#running

Alachua County Running - 20 miles: 20.02 miles, 00:10:46 average pace, 03:35:27 duration
long run… drinking the day before and was surprised i got this done. it really felt light the majority of the time. oh man, the massey park saved me with the much needed refill of water since i only had my handheld.

on a side note my daughter did great yesterday at her state gymnastics meet. 1st on bars and 4th overall while winning a slot to regionals!
#running

Run LLMs Locally with Docker: A Quickstart Guide to Model Runner
AI is quickly becoming a core part of modern applications, but running large language models (LLMs) locally can still be a pain. Between picking the right model, navigating hardware quirks, and optimizing for performance, it’s easy to get stuck before you even start building. At the same time, more and more developers want the flexibility […] ⌘ Read more

Swimming: 00:39:26 duration
playing with the kids
#swimming

Alachua County Running - 8 miles at pace: 8.03 miles, 00:08:33 average pace, 01:08:39 duration
rolling hills really did not phase me as much as i expected.
#running

Luckfox Nova Features Cortex-A35 and Onboard Audio Peripherals
LuckFox has introduced a compact Linux development board named Luckfox Nova, built around the Rockchip RK3308B. This quad-core 64-bit Arm Cortex-A35 processor runs at 1.3GHz and is designed for audio processing and smart voice applications. This device shares the same form factor as other LuckFox boards, such as the Pico Ultra RV1106 (ARM Cortex-A7) and […] ⌘ Read more

5 miles: 5.05 miles, 00:09:35 average pace, 00:48:26 duration

#running #treadmill

XMPP Interop Testing: Enabling Tests
Our project creates a framework that allows anyone to easily add XMPP standards compliance tests to the test phase of
their build pipeline. Prior to our most recent release (version 1.5.0) a test execution would basically run all tests
in the test suite. We provided an option to exclude certain tests, but in essence, the bulk of tests would execute.

This behavior is generally preferable when testing an XMPP server implementation. A benefit of exclusion-based
… ⌘ Read more

ESP32-P4-Module-DEV-KIT Introduces Wi-Fi 6, Dual-Core RISC-V, and Ethernet
The ESP32-P4-Module-DEV-KIT is a low-cost development board based on the ESP32-P4, with an integrated ESP32-C6 coprocessor. It supports Wi-Fi 6, Bluetooth 5/BLE, and is designed for embedded HMI applications and edge computing. The board features a 400 MHz RISC-V 32-bit dual-core processor for performance-intensive tasks, along with a low-power RISC-V single-core processor running at up […] ⌘ Read more

Literally Windows on arm: here is Windows running on the Pixel Watch 3
Right off the bat, there is not that much use for a Pixel Watch with Windows on it. The project, as the maker says, is for “shits and giggles” and more like an April Fool’s joke. However, it shows how capable modern smartwatches are, with the Pixel Watch 3 being powered by a processor with four ARM Cortex A53 cores, 2GB of DDR4X memory, and 32GB of storage. Getting Windows to run on Gustave’s … ⌘ Read more

Pinellas County Running - 8 miles: 8.04 miles, 00:09:24 average pace, 01:15:35 duration

#running