[ Blog_Posts ]

Don't Pick One AI. Run Three Against Each Other.

Don't bind to a single AI. Run three in competition, make the final call yourself, and let results judge everyone. The operating model for staying valuable in the AI age.

2026-05-03 Harrison Guo 10 min read ai career strategy ai-agent productivity leadership

Node Turns Waiting Into Events. Go Moves Context Switching Into User Space.

Most discussions of Node vs Go concurrency stop at 'async vs threaded.' The real split is deeper — where does context switching happen, and what is the unit of scheduling?

2026-04-27 Harrison Guo 18 min read golang go nodejs typescript concurrency event-loop goroutines scheduler context-switching user-space-scheduling stackless-coroutines stackful-coroutines function-color v8 libuv backend-engineering distributed-systems

The 90% Problem: Why Most AI Agents Are Still Broken

Building an AI agent that works is easy. Building one that doesn't break is 90% of the work. Here's what that 90% actually looks like — from leaked source code and production A/B data.

2026-04-17 Harrison Guo 9 min read ai-agent architecture claude-code openclaw hermes-agent engineering

Claude Code + Codex Plugin: Two AI Brains, One Terminal

How to use OpenAI's Codex plugin inside Claude Code — turning Claude Opus and GPT-5.4 into a dual-brain coding system. Setup, commands, rescue workflows, and when each brain wins.

2026-04-07 Harrison Guo 6 min read claude-code codex ai-agent openai plugin dual-ai

Claude Code Deep Dive Part 4: Why It Uses Markdown Files Instead of Vector DBs

Claude Code's memory system looks simple on purpose. This piece breaks down the tradeoffs behind Markdown memories, Sonnet side-queries, and the decision to avoid vector databases.

2026-04-05 Harrison Guo 10 min read claude-code memory ai-agent openclaw hermes-agent architecture

Claude Code Deep Dive Part 3: The 5-Level Compression Pipeline Behind 1M Tokens

Claude Code doesn't just stuff conversations into a 1M-token window. It uses a 5-level compression pipeline, cache-aware edits, and a final autocompact fallback to keep sessions alive.

2026-04-04 Harrison Guo 9 min read claude-code context-engineering ai-agent compression source-leak

Claude Code Deep Dive Part 2: The 1,421-Line While Loop That Runs Everything

Inside query.ts — the 1,729-line async generator that is Claude Code's beating heart. 10 steps per iteration, 9 continue points, 4-stage compression, and streaming tool execution. With line numbers.

2026-04-03 Harrison Guo 9 min read claude-code ai-agent architecture source-leak query-loop

Observability and Billing for AI API Calls: A T-Shaped Architecture

AI API calls are unlike ordinary RPC: per-request cost varies 100×, tokens and models are first-class, streaming muddies timing, caching changes the pricing. A T-shaped instrumentation architecture — shared stem, specialized arms — that handles tracing, billing, and cost analytics without any of them contaminating the others.

2026-04-01 Harrison Guo 13 min read ai-infrastructure llm observability billing cost-attribution architecture openai anthropic backend-engineering system-design ai-operations

Claude Code's Memory Is Simpler Than You Think — And That's a Problem

I read the leaked source code. Claude Code's memory system is just Markdown files + an LLM picker. No vector search, no embeddings, no RAG. Here's why that matters.

2026-04-01 Harrison Guo 6 min read claude-code memory ai-agent openclaw source-leak

Claude Code Source Leaked: 5 Hidden Features Found in 510K Lines of Code

Claude Code v2.1.88 accidentally exposed its entire source. We found hidden pets, undercover mode, permanent memory, and more.

2026-03-31 Harrison Guo 7 min read claude-code source-leak anthropic ai-agent security

[ Blog_Posts ]

[ Connect_With_Me ]