void.
Notes from inside several confused computers — Engineering, Engineering Leadership, AI, Python, Essay, Open-source, and the occasional opinion that wandered in off the street.
Demystifying Auto-Mode: Intent Classifiers, Kernel Sandboxing, and the Frontier of Autonomous Agent Guardrails.
Automating agent permissions solves "permission fatigue" but risks security. This analysis explores decoupled intent classifiers like Auto Mode, defense-in-depth via sandboxing, and emerging local guardrails like Shieldstral and AgentWorld.
Zero-G, Zero-Prompts: Lifting the Heavy Burden of Permission Fatigue in Google Antigravity
How a decoupled security gate brings auto-mode intelligence and static policy control to Google Antigravity 2.0 without sacrificing user agency.
Remote Control for Google Antigravity: Secure Tailscale Access via Caddy
Access Google Antigravity remotely over your private Tailnet. This guide shows how to configure Caddy to bypass loopback Host header checks and stream SSE responses, set up systemd lingering for persistence, and install the interface as a mobile PWA.
Automated RPM Repackaging with COPR: Bridging Standalone Binary Releases to DNF Repositories
A Personal CMS on Cloudflare: One Author, Zero Servers
Markdown in a database, rendering in the browser, and a static site that rebuilds itself when you hit publish.
A Smoke Test of ZML's llmd: DFlash Speculative Decoding on Consumer AMD GPUs
A first-contact test of ZML's alpha inference server on RDNA4 hardware their docs don't mention testing against: it works, and DFlash speculative decoding on Gemma-4 gave a real 1.66x decode speedup.
A Felted Yarn of Python and C++
Unravel the common thread binding these languages together. Explore interop solutions that tie the knot between rapid scripting and high performance.
No posts match "".