Automation & Tools

How a loop of infinite timeouts turned into three nested deadlines, a watchdog, and a repeatable method for writing agent skills that survive production.

How to build llama.cpp w/ TurboQuant and MTP and use it on consumer HW - 32GB RAM + 8GB VRAM GPU.

Playwright v1.60 introduces scoped HAR recording that captures every network request and response during a failing test, turning failures into consumable evidence for humans and AI. This guide dives deep into the new `tracing.startHar()` API, shows real-world patterns, and reveals gotchas you'll encounter in CI.

Forget Docker images and pre-built binaries. Here's how I compiled a custom llama.cpp fork with TurboQuant, ran a 26B Gemma 4 MoE model on a consumer RTX 3070, and squeezed 262K context into less than 4GB of VRAM.