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.
Moderne's Prethink materialises compiler-accurate code quality metrics as in-repo files that AI coding agents can actually read. A look at what it does, what's novel, and the honest trade-offs.
A comprehensive guide to creating interactive graph visualizations using Vis.js and Next.js 16, replacing WebGL-based libraries for better browser compatibility.
A comprehensive guide to building interactive knowledge graphs that enhance AI applications, improve retrieval accuracy, and provide better user experiences.
Microsoft's Agentic-Agile proposes a top-down methodology. But the open-source community has been running a radically different experiment — and the results are already here.
Comparing the five major approaches to building agentic AI workflows — when to use monolithic frameworks, multi-agent orchestration, or the emerging LLM router pattern for autonomous tool selection.
Why MS365 exit strategies must be developed in parallel with implementation, not as an afterthought. Digital sovereignty requires exit-by-design principles from day one.
Microsoft's DELEGATE-52 benchmark proves frontier models corrupt documents beyond 20 interactions. One week later, Google confirmed criminals used AI for a real zero-day exploit. The two findings describe the same gap from opposite ends.
A split architecture for local AI — MiniMax M2.7 extracts signals, PyMC's NUTS sampler produces calibrated posterior distributions. No cloud dependency, no LLM probabilistic reasoning, no API keys in production.
How an attacker chained pull_request_target cache poisoning with GitHub Actions memory extraction to publish 84 malicious npm packages — and what you must audit in your own CI/CD pipeline.
Run 3 specialised LLMs on a single DGX Spark in under 2 minutes with 100+ tok/s throughput. Production orchestration patterns revealed.
Dovecot's battle-tested reliability vs Stalwart's modern architecture. Resource usage, scalability, and migration considerations evaluated.
Hermes Agent combines OpenClaw's multi-channel presence with a closed learning loop for self-improving AI automation. Here's how to migrate and what to expect.
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.
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?
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.
Get notified when I publish new articles on AI infrastructure, DevOps, and XR development.