Blog Posts
- Home /
- Blog Posts

Golang disables Nagle's Algorithm by default: A performance trick on unstable networks
Hello everyone, today I want to share with you a funny and sad story that I and many of my fellow system engineers have experienced.
Read More
Obscura vs Lightpanda: When AI Agent Does Not Need a Bulky Browser
If you’re building an AI Agent or large-scale web scraping systems, you’ve probably gone crazy with Headless Chrome at some point. Every time you run puppeteer.launch({ headless: true }) or Playwright, it’s like your server screams because of the RAM consumption. Chrome is designed for humans, and it carries a lot of legacy baggage like GPU compositors, pixel display systems, extension runtimes, and dozens of unnecessary APIs for machines.
Read More
Agent = Model + Harness: Do not put an F1 engine into a brakeless bus
At the end of last year, I created a bot that ran in the background to automatically read menus from partner restaurants sent in PDF/Excel format, then parsed them into a Go struct to load into the Menu Service database.
Read More
AI in production 2026: Ford rehires engineers, Zuck admits, and an unexpected ending
“That would produce a high-quality product” - The most expensive statement of Ford in 2026 “Mistakenly we thought that by just introducing artificial intelligence and ingesting the design requirements that we had, that that would produce a high-quality product.”
Read More
LeanCTX: Context Engineering Machine for AI Agents - Not Just Token Compression
Introduction: The Day I Realized I Was Fueling a Jet with My Wave It happened like this.
Read More
Headroom vs Aphrodite: The Context Compression War - Your LLM is Burning 90% of Tokens on Junk
$80 per Bookmark In April, I was debugging a trace why the service menu was returning 500. Claude Code ran, sent the stack trace in, loaded the service file, then sent the gateway file, and also sent the DB schema. 3 seconds later - bing - it responded. After reading it, I just sat there in silence.
Read More
77.5k stars with just one idea: getting an AI agent to talk like a prehistoric person
77.5k stars with just one idea: getting an AI agent to talk like a caveman ⛏️ “Why use many tokens when few do the trick.”
Read More
From Claude Code to Hermes Agent: The Journey to Find an AI Agent That Doesn't 'Forget' Itself Every Morning
On Monday morning, I opened Claude Code, typed claude in the terminal, waited 3 seconds for loading, and then realized: it didn’t remember anything.
Read MoreDeepSeek Distillation Strategies
This post has been merged or removed. Please go back to the Home page to read the latest articles.
Read More
Trellis: Training wheels for your AI coding agent
On the first day of Tet, I sat undoing the commit that Claude Code had automatically pushed to main at 2am.
Read MoreCategories
Tags
- 9router
- Agent
- Agent-Harness
- Agnes-Ai
- Ai-Agent
- Ai-Agents
- Ai-Coding
- Ai-in-Production
- Ai-Models
- Ai-Router
- Ai-Tools
- Anthropic
- Aphrodite
- Api
- Architecture
- Automation
- Aws
- Backend
- Best-Practices
- Browser
- Cache
- Caveman
- Claude-Code
- Cloud-Cost
- Codex
- Comparison
- Concurrency
- Context
- Context-Compression
- Context-Engineering
- Cost-Saving
- Database
- Deepseek
- Devops
- Distributed-Monolith
- Filtering
- Ford
- Gemini
- Golang
- Goroutine
- Gpt-5
- Graceful-Shutdown
- Headless
- Headroom
- Hermes-Agent
- Incident-Management
- Interview
- Lean-Ctx
- Llm
- Llm-Safety
- Matplotlib
- Mcp
- Memory
- Meta
- Microservices
- Microsoft
- Models
- Monolith
- Mvcc
- Mysql
- Network
- Open-Source
- Openclaw
- Opencode-Go
- Performance
- Pi-Agent
- Plugin
- Postgresql
- Proxy
- Reality-Check
- Reliability
- Routing
- Runtime
- Rust
- Sapiensai
- Scraping
- Search
- Security
- Self-Hosted
- Setup
- Singapore
- Skill
- System-Design
- Tcp
- Telemetry
- Thinking-Budget
- Token-Optimization
- Trellis
- Web-Scraping
- Workflow
- Zig