Build it right. First-principles software design and engineering.
Joined February 2009
- Tweets 448
- Following 22
- Followers 485
- Likes 38
207 Photos and videos
Glucode retweeted
Jun 9
Everything you need to know about what we announced at #WWDC26… plus a few cameos!
126
412
5,541
323,498
Glucode retweeted
Jun 11
Apple just did something nobody expected.
They turned 2 billion iPhones into local AI machines.
They open-sourced coreai-models, the entire toolkit that lets you export any HuggingFace model and run it natively on iPhone, iPad and Mac with zero cloud.
→ Runs 100% on the Neural Engine
→ No cloud. No API keys. No subscriptions.
→ Fully offline. Your data never leaves the device.
It even ships with skills for Claude Code, Codex, and Gemini, so your coding agent already knows how to use it.
100% Open Source.
30
103
606
44,201
We’ll be watching Core AI closely at Glucode, and diving deeper into how we can help teams take full advantage of on-device intelligence.
Jun 10
This year, I had the opportunity to present at WWDC and finally share what my team and I have been working on
Core AI powers Apple Intelligence and Siri AI, and it’s incredible to see this become available to developers worldwide this week!
youtu.be/gl5lD2gEhb0?si=8EXr…
1
60
One of the more under-the-radar WWDC announcements could prove to be one of the most impactful.
Core AI allows developers to run AI models directly on Apple devices, reducing dependence on cloud infrastructure for many use cases. For businesses, this means faster experiences, lower operating costs, stronger privacy, and more capable products.
Jun 9
Apple finally did it.
Its new framework, Core AI, runs models entirely on Apple silicon, so inference happens on the user's device with zero server calls and zero token bills.
That means Qwen, Mistral, and SAM3 running natively across iPhone, iPad, Mac, and Vision Pro.
It's a memory-safe Swift API that compiles models ahead of time for near-instant load. Pulling one in takes a few lines:
let segmenter = try await ImageSegmenter(resourcesAt: sam3ModelURL)
let response = try await segmenter.segment(image: inputImage, prompt: "flower")
The launch goes beyond the runtime, though.
It ships curated open models packaged for Swift, PyTorch extensions to convert your own, and an optimizer that shrinks models layer by layer with minimal accuracy loss.
There's also a macOS debugger that profiles performance and traces behavior back to your original Python, plus Xcode tools to validate models before they ship.
For any team that wanted real on-device AI without a cloud bill attached to every user, this is the answer.
Models repo: github.com/apple/coreai-mode…
1
64
Among all the WWDC announcements, this was a pretty special moment for us.
Three products built by Glucode appeared on screen during Apple’s special event.
It’s always rewarding to see products you’ve helped build being used, recognised, and showcased on a global stage.
Jun 8
What do you know, three @glucode made apps on two screens at WWDC!
ALT The River Club
ALT Human Writes and The Club app
2
78
That’s a wrap on Glucode’s annual WWDC watch party. Missed it?
Here are the key takeaways:
• Siri AI takes centre stage
• Apple Intelligence expands across the ecosystem
• iOS 27 and macOS continue the evolution of Liquid Glass
• New opportunities for teams building Apple experiences
We’ll be unpacking what matters most for businesses, product teams, and developers over the coming week.
2
260
Most of the time, important data is harder to access than it should be.
SkyQ Mobile was rebuilt from scratch with that constraint at the centre. Native iOS and Android, architecture and UI designed around speed of access, not volume of features: glucode.com/projects/skyq-mo…
1
41