Marvin Zhang Blog

Start somewhere that has nothing to do with agents.

Writing a feature used to take all day.

If you've worked with an AI coding agent, you've seen this scene: the agent finishes a task and reports, full of confidence — "All tests pass ✅".

In April 2021 I wrote a piece on why modern software engineering can't do without project management.

On March 11, 2025, Anders Hejlsberg published a post titled A 10x Faster TypeScript: Microsoft was porting the TypeScript compiler to Go.

The AWS Summit in Shanghai, 23–24 June 2026.

A team of eight engineers has wired AI coding agents into their development pipeline.

Every AI keynote in 2026 opens with the same three slides: a bigger model, a faster chip, a smarter agent.

Six protocols.

When SWE-bench scores improved 50% in just 14 months—from Claude 3.5 Sonnet's 49% in October 2024 to Claude 4.5 Opus's 74.4% in January 2026—you'd think AI agents had conquered software engineering.

Earlier this year, I was amazed by agentic AI coding with Claude Sonnet 3.7.

Introduction: The Industrial Revolution of AI-Assisted Development 25% of Y Combinator's 2025 cohort now ships codebases that are 95% AI-generated.

The first time an AI system disagreed with my architectural decision and turned out to be right, I realized something fundamental had changed—not about AI, but about what leadership means.

Introduction: From Theory to Practice In Part 1 of this series, we established the foundational concepts of computational limits: the distinction between fundamental and engineering limits, the four-tier computational hierarchy, formal complexity measures,

Introduction: The Universal Speed Limit of Code In 1905, Albert Einstein proved something revolutionary: nothing can travel faster than the speed of light.

Introduction: The Impossible Dream of Perfect Testing "Testing shows the presence, not the absence of bugs."

Picture this: It's Monday morning, and you're sitting in yet another meeting about why your company's LLM application can't seem to move beyond the demo stage.

Introduction: The Challenge of Complex Feature Development Every developer knows the feeling of staring at a complex requirement and wondering where to begin.

"Context engineering is building dynamic systems to provide the right information and tools in the right format such that the LLM can plausibly accomplish the task." — LangChain If you've been building with AI for a while, you've probably hit the wall whe…

Introduction Recently, I successfully used GitHub Copilot Agent to migrate all my archived markdown articles to this Docusaurus-based blog, and the experience was surprisingly smooth and efficient.