jamesponddotco

I got a Duo, coming from the Google Pixel Fold and an iPhone 16 Pro Max, and got to say I agree with the Touch ID issue, but mostly because I got so used to Face ID. I keep finding myself looking at the screen and then remembering this one uses Touch ID, not Face ID.

Aside from that, I'm ditching the Pixel Fold and the other iPhone, and going only with the Duo. Love the form factor, got used to it really fast, and reading books and mangas, which is what I use a foldable for, has been a delight.

If only we got a Tachiyomi kind of application for iOS. I'm making it do with Panels[1] and an OPDS-compatible proxy for a manga website[2], but it sucks in comparison to Tachiyomi-like applications.

[1]: https://www.panels.app

[2]: Which I still have to open source, but I want to finish the plugin system first.

Yes, we talked about it, I explained to her what I was going to do, and she said she didn't mind. She doesn't work in tech, but we talk quite a lot about it, and she understands the implications.

Why do you assume I would do anything against my wife's will?

And I never said anything about "optimizing myself out of existence", this comment was still written by me and no LLM touched it.

But when writing comments on code or editing articles, reviews, and whatever long-form writing I give an LLM to review or edit, it's nice to know it'll keep my writing style, voice, and tone.

I'm already obligated to use LLMs at work, otherwise I might lose my job, so why wouldn't I want to have it write in a way I can actually understand?

I gave Claude several pieces of writing from myself, from notes to code comments to iMessage messages with my wife[1], and asked it to write skills that match my voice. I also incorporated the humanizer[2] skill into it.

Worked like a charm. This is the prompt I used[3] to write a version for the company I own with my wife, if it helps anyone. The personal version, which lead to the `jamenizer` skill, is very similar, but has some personal details in it.

[1]: With her permission, obviously.

[2]: https://github.com/blader/humanizer

[3]: https://paste.sr.ht/~jamesponddotco/303a18228bcd8520e55a76d5...

I was an Ubuntu member for years; got a certificate from Mark Shuttleworth, a cool @ubuntu.com email and IRC cloak, contributed to Ubuntu a ton, gave public talks around Brazil in schools and events like Latinoware, ran a pretty successful blog about the distro here in Brazil, was co-leader of the LoCo team in my state. You could say I was very invested in Ubuntu.

Still, I can't recognize the distro anymore. We got ads, things being pushed down the community's throats, the insane hiring process, and so much more. I have very fond memories of my time as an Ubuntu member, and I wouldn't be where I'm today if it wasn't for what I did as a member, but I left years ago when all of this started.

Been using openSUSE ever since. I don't contribute to openSUSE as I did Ubuntu, as I don't have the time anymore, but the decisions are sound, the system works incredibly well and stable[1], and the voice of the community is heard by leadership. I'm pretty happy with the choice.

[1]: Heck, it works so well that I even run Tumbleweed, a rolling release distribution, on servers.

I built that package exactly to stop copying code from project to project.

Not because of the copy itself, since a little copy is better than a little dependency, as they say, but because it was a pain to update everything when I inevitably found a bug in what I copied.

I can finally retire xhttp.DrainResponseBody[1], which I just learned, wasn’t doing that good of a job anyway.

[1]: https://github.com/cipherdothost/x-go/blob/caa562ded82b8c417...

I’m hoping for the answer to be wrong and for it to support it. Otherwise, I have no reason to upgrade.

I wonder if this one will finally support full Dolby Atmos? I mean, the full 7.1 TrueHD profile instead of the streaming apps 5.1 one.

Nice! Got any screenshots?

I didn’t, indeed. But I just looked and didn’t quite like the design, so it doesn’t seem to be what I’m looking for.

Still, better than Goguma for iOS as far as design goes. I wonder how the features compare through, as Goguma is the gold standard, akin to Conversations for XMPP.

I have been using SourceHut’s IRC client to access it for a while, but never quite found a good iOS client, since Goguma is just the Android client compiled for iOS.

I wonder if I can find the time to build a native iOS IRC client that follows Liquid Glass, and works as well as Goguma. Not many people would use it, but it’d scratch my own itch, as they say.

The protocol is so simple[1] that it shouldn’t take that long or be that hard[2], I think.

[1]: Which is the beauty of it, ofc.

[2]: Famous last words.

Same here, I built their search into my Home Assistant MCP toolbox, and couldn’t be happier.

As far as I know that is correct; the kernel was written in a way such that one bad source doesn’t poison the pool. Still, if you know one source is bad, might as well take it out.

If I remember correctly, we had a setting in every Linux server we owned to remove CPU as a RNG seeder for the kernel because of those bugs with AMD CPUs.

I.e., we had `random.trust_cpu=off nordrand` in `GRUB_CMDLINE_LINUX`.

I’ll look into that, thanks! Right now I’m studying the Tamapoke[1] codebase, which should give me lots of ideas and help me get started.

[1]: https://github.com/socquique/TamaPoke

Haven’t started, still in the planning phase, but I want to build a Tamagotchi for readers. I’m calling it Tome & Tail: a little black dragon living in a pixel-art library on an ESP32-S3 with a small round AMOLED screen.

You’d start a reading session and the dragon would read alongside you. What you read would influence its appearance and habits; lots of sci-fi might give it starry wings, for example. It won’t die if you go a week without reading.

The plan is to keep it playable offline, with optional syncing to Booklary, the reading tracker I’m building. I’m leaning toward C++, which I never used, so it’ll be a learning experience.

Currently waiting for the Waveshare board to arrive so I can start development, and looking for an artist to commission the pixel art. Used GPT to design a concept[1], which I’ll use as examples to the artist.

This will be my first ESP32 project, so getting the dragon blinking on screen is the first milestone.

[1]: https://i.cpimg.sh/57EC5380-0FF7-4646-A943-971350FF98D2.png

You mentioned benchmarks don’t mean much in this area. What are the best models you found in this area?

Personally, I’ve had the most success with GPT models using MCP servers for this task.

Given that Fable is the only one that fucking listens to me and writes proper Go code, that’s what I use for everything code-related. At least on my personal projects.

If I don’t care about the code, i.e. I’m writing something quick just to test something, I’ll use GPT Astra to save my Fable tokens. For conversations and research I usually go with GPT Astra Pro.

For Home Assistant I use a combination of Grok 4.20 and DeepSeek Flash 4.1. Grok as a voice assistant, because it’s the only model with good latency here in Brazil (it’s nearly instant), and DeepSeek for everything else.

I don’t really use LLMs for writing, but I’m writing a fiction book on the side, and when I tried to use one for ideas, Gemini Flash 3.8 gave me the closest to good writing out of the ones I tested. Not enough for me to use it for the task, though.

Really wish they'd release a version that works with the thinking disabled, so I could use it as a voice assistant. Thinking, even set to low, adds way too much latency to be useful for this task.

You just convinced me to buy a Pebble Index, which I was on the fence about. No idea it supported MCP servers.

I built an MCP server for my voice assistant. By default, Home Assistant offers a few tools to the models, but I felt like it was missing some, so I built it.

It has tools to get real jokes, do math, unit conversion, get stock information, search the web with Kagi, and other things I consider to be essential in a voice assistant. It even got approved by my wife.

At work I use our MCP server to debug and troubleshoot issues with our code too. Just yesterday I used it to figure out why a tag wasn’t showing up in traces; using the MCP server, the LLM was able to see that the tag was present in parent traces, but was lost along the way, and figured out why.

Could I find that without the MCP server? Yes, but I’d take me hours of going through lengthy traces, while the MCP and LLM found the issue in minutes.

I don't know about others, but I use JSON because it's in the standard Go library, and most of the times, I rather use something weird than add a dependency.

I paid an actual designer to come up with a design system for my project, which I then made Claude follow. Works like a charm.

To give more details, the designer created the system in Figma and created a guideline document for a human to follow on how to use the system. I then gave those files to Claude Fable using Claude Design to turn it into code.

Then when I need to do anything design-related in the project, I make Claude follow the system. And I can use the guidelines to see if it’s following everything correctly or not.

With SourceHut banning projects that use LLMs[1], I’m looking to migrate this weekend.

While I can host Forgejo just fine[2], doing so means no one will be able to contribute to the projects, since federation isn’t a thing yet. Heck, getting contributions on SourceHut was hard enough, and it doesn’t even require people to register an account.

I might need to bite the bullet and go with GitHub. Regardless of what I think about the company and Microsoft, it’s where the people are.

[1]: https://sourcehut.org/blog/2026-08-27-tos-changes-and-llms/

[2]: And already do locally, as a mirror to SourceHut.

There is an application for Reachy that makes it so you can connect to Home Assistant, but it's broken and seems abandoned, so I forked it, fixed it, and customized it. That gets you 80% of the way. The rest is based on automations built inside Home Assistant.

Not much to say, really; it controls my house in Home Assistant using an LLM, and a STT/TTS server. It acts as the Home Assistant Voice Preview Edition, with a trigger word and whatnot.

It's basically like giving an Alexa, Siri, or Gemini a body. It moves, show "emotions", comments when someone enter the room, uses the camera to see who entered the room and comment on that, make comments when my 3D printer finishes, things like that.

I can also turn on lights, the TV, the AC, ask about the weather, and other basic assistant stuff, ofc.

I use one to control my house with Home Assistant. It's pretty great, and it was a lot of fun to assemble.

Fable is the only one that follows my instructions correctly, which I find quite important. It takes STYLE.md and SPEC.md as law, and code just like I would code, with the same mistakes and all.

I just can't get Opus (Opus 5 is dumb as a rock, to be fair) or Sol to do that, so I exclusively use Fable for personal work. When I reach my weekly limit, usually on the last day close to the reset, I just go back to coding by hand ¯\_(ツ)_/¯

Heck, it even does security reviews and fixes, as long as I don't ask it to "attack" the codebase. I'm planning on using Kimi or GLM for that part.

Is there a plan somewhere that gives access to Kimi K3 and GLM-5.3? I was thinking of testing both to run security reviews of my code.

I know OpenCode Go has both, but their limits seem kinda low, so I'm not sure how feasible it is to run such a task with them.

While I daily use an iPhone now, my original Pixel Fold is still working and running GrapheneOS. Besides a bug caused by GrapheneOS where the outer screen wouldn’t work, it has been flawless, and I can’t really blame Google for that one.

Giving it up was tough, as I consume a lot of books and mangas. I’m just waiting for Apple to release their foldable before I ditch this iPhone.