Category: AI

  • How Github was hacked

    How Github was hacked

    To understand that first we need to trace the sequence of events before it’d happened. And, God, there were MANY: Coincidence? Outages stopped only after May 26. Looks like the hackers were trying different approaches since at least February or actively pulling the data from the servers. And while the Github CyberSecs were hunting them…

  • Was it finally fixed, Vercel?

    Was it finally fixed, Vercel?

    It seems not a day goes by without some cloud outage or critical vulnerability issue. Let’s try to analyze the recent CloudFlare outage (not again 😩) caused by the react server components. The issue is very critical. Basically any unauthorized client can execute an arbitrary code on the server.

  • I’ve brought neural style transfer to the Q3A engine — and the results are wild.

    I’ve brought neural style transfer to the Q3A engine — and the results are wild.

    Imagine Matisse, Picasso, and Van Gogh stepping into a 3D arena: the iconic shooter reborn as a surreal, living museum. Brushstrokes meet rocket jumps. Art meets chaos.

  • New XCode 26 coding assistant review

    New XCode 26 coding assistant review

    I know it’s Beta and lots of bugs to be fixed but few words just for you to understand what you’re getting with a new update this fall (EOY, next year?). Agent mode by default It’s a default setting unless you start asking questions and stop giving commands. Not joking that’s how it works 😅…

  • Testing different models for real-time style transfer

    Testing different models for real-time style transfer

    Testing a Ghibli style model The image below was used as style target for training the model. My own custom Liquid Glass design model My friend the Chicken is helping testing different models and frameworks

  • Choosing the Best AI Framework for Real-Time Apps

    Choosing the Best AI Framework for Real-Time Apps

    Ok… you’ve decided to build a real-time AI app. What framework do you choose for it? The answer is not trivial at all. Inference performance is matter more than you think for real-time solutions especially on mobile devices. The market is filled with various solutions which are not compatible with each other. When it comes…

  • Neural Style Transfer: Challenges with Apple’s AI Ecosystem

    Neural Style Transfer: Challenges with Apple’s AI Ecosystem

    Diving into Apple’s NPU, it’s a mess! The ANE is underused and can’t handle workloads solo, so it’s always relying on CPU/GPU. OpenCL’s gone, and conversions between models are glitchy. For AI to flourish here, Apple needs to open up, support standards, and get ANE properly utilized. Good luck, Apple!

  • Made a weirdly satisfying style transfer webcam app in C++

    It’s amazing how C++ ecosystem has evolved just for recent 10 years. Made an AI-powered app in just a couple of days. Probably with a little optimization can be the next cutting edge cross-platform AI-conference call app.