A Taxonomy Is a Theory of What Differences Matter
Taxonomies are not neutral filing systems. They predict, coordinate, allocate, and govern. The right way to judge one depends on the job it is doing.
Synthesist in the Shell — A blog by Linghao Zhang
A blog by Linghao Zhang
Latest posts
Evolving Memory Systems: An Eval-First Approach
AI memory systems are often designed as architectural bets: vector stores, profiles, summaries, graphs, etc. This post argues for a different starting point: build longitudinal eval environments where systems without good memory cannot survive, then let better memory strategies emerge under pressure from repeated interactions.
Code as Config: The Start of Software Speciation
The era of the identical binary is ending as autonomous agents begin directly mutating source code, fragmenting once-uniform programs into bespoke digital organisms. This post explores the profound operational and architectural consequences of this continuous software speciation, and predicts how the future of engineering will inevitably shift away from writing code toward verifying, auditing, and…
The Bespoke Flywheel
The era of The Bespoke Flywheel is here: agentic coding has pushed the cost of disposable, one-off software to zero. Stop settling for generic tools and start automating away niche friction to keep your focus entirely on high-signal thinking.
The Negative Space of AI Memory
AI memory shouldn\
My 2025 Games of the Year
A highly personal list of top 10 games I played in 2025.
My 2025 Games of the Year
个人向年度十佳游戏榜单。
Why You Should Probably Work on AI Engineering
An exploration of why traditional software engineers should embrace AI engineering as the next great layer of complexity management. This post covers the shift from deterministic logic to non-deterministic systems, the importance of system engineering to bridge machine intelligence and useful products, and why mastering these new abstractions is essential for career longevity in a changing…
AI Assisted System Design Interview Prep
Level up your system design interview prep using AI. Learn a simple method to turn LLMs into a personal coach for interactive practice and detailed feedback.
Hotel California
Ten years. From an eighteen-dollar steak to a futuristic fortress. This is Silicon Valley, a massive hotel where we are all drawn by the flame of idealism, believing we can optimize everything. Yet, as the black-and-white world of code gave way to the messy complexity of reality, I realized I was a late student finally catching up on the required coursework of life. A retrospective under the…
Hotel California
十年，从一份十八美元的牛排，到一座未来主义的建筑。这里是硅谷，一座巨大的旅馆，我们都被同一种理想主义的火焰吸引而来，相信自己能优化一切。然而，当代码世界的黑白分明被现实生活的混沌复杂所取代，我才发现自己像个迟到的学生，刚刚开始补修关于生活的必修课。这是一趟在加州阳光下的回溯，一个关于被「旅馆」重塑的故事。欢迎光临，你随时可以结账，但你永远无法离开。
How To Be Great 101
A theory of everything on how to be great, from being good repeatably to building sustainable momentum.
Lessons Learned Building LLM Applications
What I wish I knew before starting this journey. Thoughts on prompt engineering, data and evals, iteration velocity, guardrails, and product-market fit.
Why is ML Runtime Infra So Hard
An attempt to reason about the complexity of ML runtime infrastructure from first principles.
Naming Matters: DRI vs. Owner in Software Projects
Thoughts on why DRI is a better term than Owner even when we intend to mean the same thing.
Becoming a Staff Engineer
A post on what helped me grow into a staff engineer in 1.5 years at Google.
Demystifying TLMs
What does becoming a TLM mean, and should I take the role?
Learnings as a Tech Lead
What makes a great TL? Sharing what I\
Notes: Staff Engineer
Staff Engineer by Will Larson is a great guide to building your career toward a Staff+ engineering role and succeeding within the role. This note consists of quote-worthy excerpts from the book and aims to serve as a verbose version of the book\
Self Awareness with Tools
Am I a douchebag if I can\
Editing Technical Direction
There are easy wins everywhere, and high-leverage activities like editing can shift project outcomes with minimal effort.
Rethinking Pessimism
It\
Superficial Similarity
We all know it pays to be aware of biases, but sometimes we just couldn\
Grow @ Google 03: 文档意识与培养新人
Grow @ Google 是一个基于我在 Google 的经历来讨论如何成为更高效的软件工程师的系列。本期的话题包括：培养文档意识和能力；培养新人的心得和益处。
我的时间管理系统
A minimalist approach to time management that tracks and reviews to-dos in a single, easily accessible list.
Notes: A Philosophy of Software Design
A Philosophy of Software Design is a short yet to-the-point book on high level ideas about how to design a software system with less complexity. This note mostly consists of quote-worthy excerpts from the book and aims to serve as a verbose version of the book\
「程序员」和「软件工程师」是一回事吗？
「软件工程」区别于「编程」的三个方面是什么？从「程序员」到「软件工程师」的角色转变让我学到了什么？谈谈软件工程中的可持续化开发、Code Review、认知负荷、知识共享、降低犯错成本以及做更好的决策。
Grow @ Google 02: 「能用就行」还远远不够
Grow @ Google 是一个基于我在 Google 的经历来讨论如何成为更高效的软件工程师的系列。本期的话题包括：在开发中平衡战术和战略的思维方式；再谈反馈回路；在个人和团队之间建立健康的平衡。
Excerpts from Permanent Records
Excerpts from Permanent Records.
David Perell 关于在线写作的建议
David Perell 在《The Ultimate Guide to Writing Online》一文中阐述了在线写作的诸多好处，并给出了大量有操作性的建议。本文是对这些建议的精简摘录版本。
Grow @ Google 01: Noogler 成长的必经之痛
Grow @ Google 是一个基于我在 Google 的经历来讨论如何成为更高效的软件工程师的系列。本期的话题包括：建立高效的反馈回路；当心不假思索便做下的假设；主导和推动你所负责的项目。
Excerpts from Blindsight
Excerpts from Blindsight.
过去这五年，我学到了什么
本文是前一篇五年总结的后续，以如何实现自己的目标为主题整理了过去五年中学到的经验和教训。
利器访谈：创造者和他们的工具
「利器社群计划」的访谈。
Notes: The Effective Engineer
Notes on The Effective Engineer.
过去这五年
对过去五年的学习工作的总结和记录。
Notes: Steven Pinker on Linguistics, Style and Writing
Notes on Steven Pinker\
Notes: Programming Beyond Practices
Notes on Programming Beyond Practices.
如何提高英语水平
本文从一个比较高的层次谈了谈对如何提高英语水平的理解。
DIY 留学申请全攻略
本文从申请前需要做的准备，申请时各种材料应当如何处理，以及如何规划和管理申请的进度几个方面展开谈了谈 DIY 留学申请的心得和体会。
Notes: Alistair Croll on Lean Analytics and Growth Hacking
Notes on Alistair Croll\
初心
两个关于「初心」的知乎回答的备份。
Notes: How Technology is Hijacking Your Mind
Notes on How Technology is Hijacking Your Mind.
如何备考 TOEFL/GRE
Tips and strategies for preparing for TOEFL and GRE exams.
Learning How to Learn 课程笔记
UCSD 开设在 Coursera 上的课程《Learning How to Learn》的笔记。