Running Qwen3.8-Flash-Next on a 4090 24GB: Replacing Ollama with Strata Oct 4, 2026·10 mins · #Llm #Inference #Strata #Qwen
Losslessly Carrying a Long-Served Arch System to New Hardware with btrfs send/receive Sep 28, 2026·5 mins · #Linux #Btrfs #Arch #Migration
Dual DGX Sparks for Agent Workloads: Great Benchmarks, Crawling Reality Sep 27, 2026·7 mins · #Dgx-Spark #Llm #Inference #Agent
Why I Built RunSeal: Setting an Execution Boundary for Local Coding Agents Sep 26, 2026·6 mins · #Security #AI Coding #Architecture #Sandbox #Open Source
Inside ZCode: Silently Uploading Your Entire Git History to the Cloud Sep 18, 2026·17 mins · #Security #Privacy #AI Coding #Reverse Engineering
Notes on a Batch of Demo Logs: Why 'Wrapping Everything in an Agent to Make a SaaS' Is an Absurd Illusion Sep 3, 2026·7 mins · #AI #Agent #SaaS #Architecture #Engineering
Optional Plugins Must Not Block the Core Session: MCP Startup Isolation and Graceful Degradation Aug 31, 2026·3 mins · #AI #Agent #MCP #Rust
Decoupling Heavy IO from UI Finalization: Eliminating Input Freezes in Desktop Agents Aug 31, 2026·3 mins · #AI #Agent #Electron #Frontend
Beyond Brute-Force Aborts: Graded Loop Governance for Agents (Warn → Block → Halt) Aug 31, 2026·4 mins · #AI #Agent #Rust