[ Blog_Posts ]

Claude Code Source Leaked: Kairos, Undercover Mode, Ultraplan — 5 Hidden Features (510K Lines)

Claude Code v2.1.88 accidentally exposed 510K lines. The 5 hidden features: Kairos (permanent memory), Undercover Mode (stealth), Ultraplan (deep planning), Pet System (Buddy), Multi-Agent. Source-cited.

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

Consistency in Distributed Systems: Scenarios, Trade-offs, and What Actually Works

Strong, eventual, causal, read-your-writes, linearizable — consistency models are taught as a taxonomy. Production uses them as a menu. Ten scenarios, the right consistency choice for each, and the engineering that makes the choice work.

2026-03-28 Harrison Guo 15 min read distributed-systems consistency cap-theorem pacelc eventual-consistency linearizability saga crdt database system-design backend-engineering

The AI Stack Explained: LLM Talks, Program Walks

A first-principles breakdown of the entire AI stack — from LLM to Agent in one mental model. An LLM can only output text. Everything else is the program.

2026-03-28 Harrison Guo 8 min read ai llm function-calling mcp agent rag ai-architecture first-principles

gRPC Interceptors in Production: Design Patterns That Survive Real Load

gRPC interceptors are where cross-cutting concerns live — auth, tracing, retry, metrics, rate limiting. Most examples online show toy single-interceptor demos. Production systems need to stack, order, and compose them correctly. A practical guide.

2026-03-24 Harrison Guo 9 min read golang go grpc interceptors middleware distributed-systems observability backend-engineering api-design microservices

Go Generics, One Year In: Which Promises Held, Which Didn't

Go 1.18 shipped generics in March 2022. Four years later, the honest picture: they're useful for a narrower set of problems than the community hoped, they fit naturally in a few places, and overuse them and your code gets worse. A production retrospective.

2026-03-18 Harrison Guo 8 min read golang go generics type-parameters software-engineering api-design backend-engineering language-design

Go Profiling in Anger: pprof, Escape Analysis, and Inlining Without Magic

Most performance advice for Go is ritual — 'use sync.Pool,' 'avoid interface boxing,' 'preallocate slices.' Useful sometimes, hollow often. A production engineer's guide to profiling Go systems with pprof, reading escape analysis output, and understanding when the compiler actually inlines.