mastodon - Link to source
I booked the one-way ticket! Going to fly to central Europe on Oct 26 and do a little traveling before settling up north in Oslo. It still doesn’t feel real. I’ll be posting Reels like this about the experience on my IG, so feel free to follow along! instagram.com/share/_4aHW0lK7

Sommer Panage on Instagram: "Moving abroad in T - 40 days … overwhelmed is an understatement!"

Renewing your passport abroad can be a daunting task, but with the right guidance, it's achievable in just 40 days.
Instagram

mastodon - Link to source

"Screen readers do not need to be saved by AI"

TetraLogical's @craigabbott has written a post on his own blog exploring why we shouldn’t expect screen readers to be augmented with AI to fix problems with bad content.

The real problem is producing inaccessible content from the start, such as misusing emojis, poor descriptions, or unclear writing.

craigabbott.co.uk/blog/screen-…

#Accessibility #ScreenReaders #InclusiveDesign


Screen readers do not need to be saved by AI

Why LLMs should not be integrated with screen readers
Craig Abbott (craigabbott.co.uk)
#Accessibility #screenreaders #inclusivedesign @Craig Abbott

reshared this

in reply to TetraLogical

mastodon - Link to source

Matt Campbell

As a former screen reader developer myself, I mostly agree with this article. But, for the specific exzample of the clapping hands emoji, I think it would be easy enough to add a special case to the screen reader -- not "AI", but just a good old hand-coded heuristic -- to filter the text and then play a clapping-hands sound effect synchronized with each of the words. I just wonder if there's broad consistency on whether the emoji comes before or after the word.

Matt Campbell reshared this.

in reply to Matt Campbell

mastodon - Link to source

Glyph

@matt I really feel like this insistence that people not add "fun" expressions to their language is never, ever going to be a viable strategy for addressing accessibility more broadly. Gen alpha slackers attempting to use indecipherable emoji algospeak to impress their friends or evade algorithmic filters in their Instagram posts are not going to be persuaded to read a 216-page $30 book before they write anything.
@Matt Campbell
in reply to Glyph

mastodon - Link to source

Craig Abbott

@glyph @matt you’re right, people aren’t going to randomly just pick up a book and read about it. But, I think education is a key part to all of this. I just think it needs to be taught it earlier, in things like key skills communications, and computer science curriculums. Accessibility doesn’t get taught during those formative years, where it would likely have the most impact. We’re trying to re-teach every new generation retrospectively.
@Matt Campbell @Glyph
in reply to Glyph

mastodon - Link to source

Glyph

@matt Like, Know Your Meme added a "clap emoji" entry 9 years ago. Why are we carrying water for NV Access for failing to implement anything to detect that pattern for nearly a decade? Does *Apple* not have the resources to code the ability for VoiceOver to interpret the 10 or so most popular unicode & emoji idioms at the rate of one per year? Saying we need to train kids to avoid fun rather than demand more from these companies seems backwards.
@Matt Campbell
in reply to Glyph

mastodon - Link to source

Matt Campbell

@glyph You're definitely right about Apple. I'm much more sympathetic toward NV Access, because they're a tiny non-profit working on an open-source project. And if I remember correctly, NVDA only gained an internal TTS API rich enough to support sound effects synchronized to individual words in like 2019 or 2020. (I had written that feature in 2003, for the purpose of indicating links with a tone, but I can understand having different priorities.)

@craigabbott @TetraLogical

@Glyph @Craig Abbott @TetraLogical
in reply to Matt Campbell

mastodon - Link to source

Matt Campbell

@glyph The company that I _really_ think we shouldn't carry any water for is Vispero, the current owner of JAWS. Clearly at this point the company is mainly trying to squeeze more money out of what IMO can justifiably be described as the WinZip of screen readers. I make that comparison deliberately; WinZip was at one point owned by the same private equity group that invested in Vispero. And both products now have high-quality free counterparts.

@craigabbott @TetraLogical

@Glyph @Craig Abbott @TetraLogical
in reply to Matt Campbell

mastodon - Link to source

Matt Campbell

@glyph To clarify, when I said "I wrote that feature in 2003", I meant I implemented sound effects synchronized with TTS _in my company's own product_. And I was still entirely new to developing a screen reader, or more precisely, a talking web browser, back then. I was also quite new to _using_ a GUi screen reader, so I brought my own ideas about how they should work. Maybe the current screen readers are getting long in the tooth and it's time for a new generation.
@Glyph
in reply to Glyph

mastodon - Link to source

Glyph

@matt I am just frustrated with the way that a lot of the way accessibility breaks through as a topic into broader conversations is "look at this common mode of communication. look at this hilarious failure mode that a screen reader has when it's used. now that you know that, everyone stop doing it". It's practically a meme template at this point. I'm sure that you've done tons of other great stuff on the subject that I've never seen because it didn't break through.
@Matt Campbell
in reply to Glyph

mastodon - Link to source

Glyph

@matt To keep things on the topic of your actual words, I do disagree with the sentence from your article: "The responsibility for accessibility lies with the person creating the content". This is individualizing a systemic problem. It's applying scaling leverage at the most inefficient point. Fix ~100 screen readers or train a billion or so sighted people? One of Those numbers is much smaller than the other.
@Matt Campbell

mastodon - Link to source

Waiting until THIS week to patch all the potholes that have existed since the March/April thaw!

Montréal ‘patches’ potholes ahead of weekend marathon... just to make sure people don't break legs and sue the city, I guess, eh.

ctvnews.ca/montreal/article/mo…

#polMTL #MTLpoli #montreal


Montreal ‘patches’ potholes ahead of weekend marathon

City spokesperson Philippe Sabourin says roads have already been patched to ensure the Marathon Beneva de Montréal unfolds safely.
Anastasia Dextrene (CTVNews)
#polmtl #montreal #mtlpoli
This entry was edited (1 month ago)

mastodon - Link to source

This week's bumper In-Process is out! Featuring:
- NVDA 2025.3 Released
- Using Chromium with the mouse issue
- We've been to WBU AND Something Digital
- and using Single Letter Navigation with web apps.

All that and more at: nvaccess.org/post/in-process-1…

And don't forget to subscribe to receive future posts by email: nvaccess.org/newsletter

#NVDA #NVDAsr #News #Blog #Newsletter #NewVersion #Chrome #Chromium #WBU #WBU25 #SomethingDigital #Tips #FOSS

NV Access

NV Access Email Forms
nvaccess.org
#foss #blog #chromium #chrome #nvdasr #News #newsletter #nvda #tips #newversion #somethingdigital #wbu #wbu25

pleroma - Link to source

I finally got my first real Z-Wave device and I struggled forever to get it to pair. Then I realized when I put my controller in debug I could see it come online and report that it was in the EU region.

After much twiddling and fiddling, I figured out how to start up the Z-Wave-JS-UI on my Mac, plug the controller into my Mac, and then dig into the settings where it let me define the region as USA.

Smashed that save button, plugged it back into my server and restarted services, tried to pair with the Z-Wave device again and it instantly worked.

Other than that initial fussing it seems like this is very simple to add devices to your network.

mastodon - Link to source

The movie "Hackers" was released 30 years ago today. It still stands as my favorite hacker movie. What is your favorite "Hackers" movie quote?

Here are some reasons why it remains my favorite:

- The hacker handles suggested by Joey were aliases of real hackers (at the time)
- The books passed around at the club were all real
- The soundtrack
- The Emanuel Goldstein reference (And many other references to hacker people)
- The Ginsberg quote is relevant to Hacker culture

mastodon - Link to source

Ken Thompson, 1984: Whenever you use other people's software, you should think about why you trust it.

npm, 2010: LEEEEROY JENKINNNNNSSSSSSS!

krebsonsecurity.com/2025/09/se…


Self-Replicating Worm Hits 180+ Software Packages

At least 187 code packages made available through the JavaScript repository NPM have been infected with a self-replicating worm that steals credentials from developers and publishes those secrets on GitHub, experts warn.
krebsonsecurity.com

mastodon - Link to source

Gajim 2.3.5 has been released! 🥳

This release brings reorganized account settings 🔧, a brand new shortcuts manager ⌨️, more contact infos ℹ️, video previews 📺 , performance improvements 🚀, and many bugfixes.

Thank you for all your contributions ❤️ Let us know what you think!

Support Gajim's development: liberapay.com/Gajim

#gajim #xmpp #chat

gajim.org/posts/2025-09-11-gaj…

Gajim 2.3.5 main window

Gajim 2.3.5

What’s New Gajim 2.3 comes with a new design featuring Adwaita, a user interface library which provides building blocks for modern adaptive applications.
gajim.org
#xmpp #chat #gajim

Nicoco reshared this.

mastodon - Link to source
For those of you who like the nerdy Geekbench stuff, here's the Nucbox K11 (the GMKTec one) tested: 2467 Single-Core Score, 12499 multi. Not bad at all, an M4Pro would still beat it by 60-70% faster, but still, for X86 it's actually faster than my Intel CPU was.
browser.geekbench.com/v6/cpu/1…

GMKtec NucBox K11 - Geekbench

Benchmark results for a GMKtec NucBox K11 with an AMD Ryzen 9 8945HS processor.
browser.geekbench.com
in reply to Jakub Steiner ⭐

friendica - Link to source

Schmaker

Ono to imho nebude špatný ani v tý světlý, jen to nebude tak výrazný. 420 je myšlený jako česká volačka? :)

Musim s @Archos zkusit domluvit nějakou sandbox instanci, kde bychom to zkusili nasadit a poladit, než to dáme na hlavní.

Šlo by udělat statický logo s "utíkajícím" efektem na písmenech a průhledným pozadím? Ideálně .webp (afaik animace umí, reálně si nejsem jistej :) )? :)

@Archos

mastodon - Link to source

A milé děti, takhle vypadá slovní salát… aneb když někdo píše o něčem, čemu vůbec ale vůbec nerozumí…

lupa.cz/clanky/cesi-jako-jedni…


Češi jako jedni z prvních na světě spustili komerční síť, kterou nejde odposlouchávat. Využívá částice světla

CETIN ve spolupráci s O2 rozjel jedno z prvních komerčních nasazení kvantové distribuce klíče. Může se objevit i v 5G jádře. Uvnitř: GALERIE.
Jan Sedlák (Internet Info, s.r.o.)

pleroma - Link to source

Let's ask Claude about what it would be like to use a fancy Quantum Computer for LLM inference, for example

> Would a Quantum Computer be good at the types of work required by an LLM inference engine?

⏺ No, quantum computers would not be good for LLM inference engines.

LLM inference is primarily matrix multiplication and linear algebra operations that run efficiently on classical hardware like GPUs and TPUs. These
operations involve:

- Dense matrix-vector products
- Element-wise operations
- Memory-intensive data movement

Quantum computers excel at specific problems like factoring, optimization, and simulation of quantum systems, but they're not well-suited for the
dense, classical computations that dominate LLM inference. Current quantum hardware also has significant limitations like decoherence, error rates, and
the need for extremely low temperatures.

Classical accelerators (GPUs, TPUs, custom AI chips) remain far superior for LLM workloads.

Shit you mean to tell me that this breakthrough technology is not good at matrix multiplication and linear algebra? Wild stuff

mastodon - Link to source

Firefox, I will tell you right now, as a blind person:

Please do not hold accessibility support behind a progressive rollout. You are locking certain people from using it based on effective RNG, and I don't approve.

If you release accessibility support, that's awesome - but please release it for everyone. Please. I beg of you.

firefox.com/en-US/firefox/143.…


Firefox 143.0, See All New Features, Updates and Fixes

Firefox
This entry was edited (1 month ago)
⇧