We use privacy-friendly analytics to understand how visitors use this site. No cookies are set by default. Privacy Policy
Educational materials, tutorials, and lecture notes on statistics, machine learning, and AI, plus conference talks and presentations. This includes fundamentals of AR, MR, and VR development (Machine Learning for data science, VR Fundamentals & WebXR Development, 3D Interaction Design, Performance Optimization), as well as research-based teaching on GenAI applications in Virtual Reality, eye tracking and bio sensors in immersive systems, and digital sovereignty and privacy-preserving technologies.
DeepSeek V4 ships two open-weight MoE models — a 1.6T Pro and a 284B Flash — with novel sparse attention, FP4 quantisation, 1M token context, and validated Huawei Ascend NPU support. Here's what actually changed.
Canonical ships Ubuntu 26.04 'Resolute Raccoon' with kernel 7.0, GNOME 50, Wayland-only desktop, Nvidia CUDA and AMD ROCm in the box, and a dual-track container stack. Here's the DevOps migration guide.
Wie DeepMinds AlphaDev neue Sortieralgorithmen entdeckte, die heute auf Milliarden Geräten laufen — und warum diese Methode die Grundlage für die nächste Generation der Softwareoptimierung ist.
Von der Polynommethode bis zu evolutionärer Programmsuche — wie DeepMinds FunSearch die größte Verbesserung der unteren Schranke für Cap-Sets seit zwei Jahrzehnten fand.
Alibaba released Qwen3.6-35B-A3B on 16 April 2026, the first open-weight model in the Qwen3.6 series. The benchmarks show real gains in agentic coding, but the architecture is unchanged from Qwen3.5 and the red flags warrant scrutiny.
Google now measures more than half of all traffic over IPv6, a threshold the protocol has been approaching since its specification in 1998. What took so long, and what changes next?
The failure modes that plague distributed systems appear identically in multi-agent AI teams: stale locks, split brain, cascade failures, and Byzantine faults. The solutions are decades old.
How Apple's LGTM framework breaks quadratic compute scaling in feed-forward 3D Gaussian Splatting, enabling 4K novel view synthesis for Vision Pro and spatial computing.
How CoreCoder reverse-engineered Anthropic's Claude Code from 512K lines into a minimal 950-line implementation, revealing the essential architecture of modern AI coding agents.
MemPalace stores verbatim conversation history with semantic search, achieving 96.6% recall on LongMemEval with zero API calls and zero cloud dependency.
An attacker bought 30+ WordPress plugins on Flippa for six figures, planted a dormant backdoor, waited eight months, then activated it to serve SEO spam to Googlebot across hundreds of thousands of sites.
How visionOS 26.4's NVIDIA CloudXR integration with dynamic foveated streaming transforms Vision Pro from standalone to hybrid rendering, enabling 4K PC VR games and enterprise design review.
Three research teams at IEEE S&P 2026 demonstrated that Rowhammer bit-flips on NVIDIA GDDR6 memory can bypass IOMMU protections to achieve full CPU privilege escalation.
The Hailo-8 AI accelerator cannot run LLMs. Here's what it can do alongside Gemma 4 on a Raspberry Pi 5, the real commands to set it up, and when to upgrade to a chip that actually handles language models.
Researchers from Johns Hopkins demonstrated that GitHub PR titles and issue comments can hijack Claude Code, Gemini CLI, and Copilot Agent to steal credentials, all without an external command-and-control server.
YARA identifies malware by matching binary patterns — and YARA-X, its Rust rewrite, is 5-10× faster on regex-heavy rules. Combined with IOC scanners and Sigma rules, you can catch threats before they reach production.
A 26-person startup spent $20M training a 400B MoE model on 2,048 B300 GPUs — and produced the strongest open reasoning model outside China. Trinity-Large-Thinking ranks #1 on τ²-Airline at 1/28th the cost of Claude Opus 4.6.
A technical comparison of vLLM and SGLang, the two leading open-source LLM inference engines, covering architecture, performance, and when to pick each one.
Get notified when I publish new articles on AI infrastructure, DevOps, and XR development.