Thoughts on AI/ML engineering, production systems, and technical deep-dives.https://danielzhangau.github.io/en-auhttps://danielzhangau.github.io/blog/macos-vpn-split-tunneling/https://danielzhangau.github.io/blog/macos-vpn-split-tunneling/How I built a client-side split tunneling system for macOS that routes local traffic direct and keeps international traffic on VPN. Covers IP-based route splitting, reversed DNS splitting (clean DNS via VPN tunnel + local DNS for CDN optimization), and a launchd auto-watch daemon.Sun, 17 May 2026 00:00:00 GMTmacOSNetworkingVPNSplit TunnelingShell ScriptingDevOpshttps://danielzhangau.github.io/blog/claude-code-deepseek-v4/https://danielzhangau.github.io/blog/claude-code-deepseek-v4/How I built claude-ds — a drop-in wrapper that runs Claude Code with DeepSeek V4 as the backend. Covers the architecture, environment variable reverse-engineering, vision workarounds, and honest tradeoffs from daily use.Wed, 29 Apr 2026 00:00:00 GMTClaude CodeDeepSeekAI ToolsOpen SourceCost Optimizationhttps://danielzhangau.github.io/blog/claude-code-productivity-guide/https://danielzhangau.github.io/blog/claude-code-productivity-guide/A practical guide to configuring Claude Code for maximum productivity — covering the layered configuration architecture, hooks for 100% enforcement, MCP server integrations, plugin ecosystem, context management, and worktree-based parallel development.Fri, 24 Apr 2026 00:00:00 GMTClaude CodeAI ToolsDeveloper ProductivityMCPAgentic AIHarness Engineeringhttps://danielzhangau.github.io/blog/ai-landscape-spring-2026/https://danielzhangau.github.io/blog/ai-landscape-spring-2026/A comprehensive knowledge guide covering frontier model releases, agentic AI, MCP vs function calling, the evolution of RAG, edge AI with small language models, and what it all means for AI engineers.Sat, 18 Apr 2026 00:00:00 GMTAILLMAgentic AIMCPRAGEdge AIhttps://danielzhangau.github.io/blog/harness-engineering-ai-agents/https://danielzhangau.github.io/blog/harness-engineering-ai-agents/A deep dive into harness engineering — the emerging discipline of designing systems, constraints, and feedback loops that make AI agents reliable in production. Covers core architecture, real-world case studies, and practical implementation.Sat, 18 Apr 2026 00:00:00 GMTHarness EngineeringAI AgentsLLMContext EngineeringProduction AIMLOpshttps://danielzhangau.github.io/blog/welcome/https://danielzhangau.github.io/blog/welcome/A brief introduction: who I am, what I've built, and what you'll find on this blog about AI/ML engineering in production.Fri, 17 Apr 2026 00:00:00 GMTGeneral