> For the complete documentation index, see [llms.txt](https://weekly-essay.mikey.wang/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://weekly-essay.mikey.wang/mikey-wangs-memos.md). # Mikey's Memos I’m Mikey, a long-term thinker who has grown from software engineer into builder. This is where I record my ongoing observations on AI, software engineering, product, business, and personal productivity systems. I care more about the structural changes behind the tools: how technology reshapes organizations, business, and individuals. If you value hands-on experience, independent judgment, and a long-term perspective, you can subscribe via RSS. {% updates format="full" %} {% update date="2026-08-03" %} ## W32 - A Builder’s Mac Also Needs a Sweeper A Mac environment needs clear ownership of runtimes and proxies, and it needs Sweeper plus a verifiable loop to continuously discover, converge on, and govern resource drift. Read the full article: {% endupdate %} {% update date="2026-07-27" %} ## W31 - DeepSeek Through Leaked Materials: Compute, Technical, Financial, and Organizational Constraints A highly likely leaked closed-door DeepSeek discussion exposed constraints in compute, technology, finance, and organization, and also showed how leaks raise the trust cost of fundraising. Read the full article: {% endupdate %} {% update date="2026-07-24" %} ## W30 - Model × Harness: The Idea of Intelligent Routing The combination of the model and the harness jointly determines the cost and quality of coding agents. The next layer of infrastructure will keep evaluating enterprises’ private tasks and route requests to the Pareto-optimal configuration. Read the full article: {% endupdate %} {% update date="2026-07-13" %} ## W29 - The Boundary Between Loop Engineering and RSI Loop Engineering is already a real form of productivity; RSI is still a capability boundary we are approaching. The key question is whether the loop changes task outcomes, processes, or the mechanism that produces the next generation of capabilities. Read the full article: {% endupdate %} {% update date="2026-07-06" %} ## W28 - AI Repricing Tool Software AI is lowering the cost of building personalized tools. The moat for tool software will shift from feature coverage to reliably and stably completing end-to-end workflows. Read the full article: {% endupdate %} {% update date="2026-07-01" %} ## W27 - The Builder’s Personal Productivity System The key to combining everyday tools into a personal productivity system is not the number of tools, but creating a closed loop between information, tasks, and output. Read the full article: {% endupdate %} {% update date="2026-05-18" %} ## W21 - The Inflection Point of Software Engineering Software engineering is shifting from “people write code” to “people design constraints, and agents implement them,” moving engineering value upward. Read the full article: {% endupdate %} {% update date="2026-05-11" %} ## W20 - Heuristic System and the Checkout Strategy Platform By rebuilding checkout strategy management through a Heuristic System, this piece discusses how complex strategies can gain a unified way to express, validate, and evolve. Read the full article: {% endupdate %} {% update date="2026-05-04" %} ## W19 - Taste Will Become the New Core Skill As AI lowers execution costs, judging what is worth doing and what counts as good will become a scarcer core skill. Read the full article: {% endupdate %} {% update date="2026-04-13" %} ## W16 - No-Code, Rapid Iteration, and New Engineering Constraints No-code and AI speed up iteration, but they also amplify engineering constraints around architecture, quality, and long-term maintenance. Read the full article: {% endupdate %} {% update date="2026-03-23" %} ## W13 - Meituan’s Q4 Earnings and Why the AI Era Needs a Unified, Efficient Toolchain Starting from Meituan’s Q4 earnings and AI engineering practice, this piece discusses why teams need a unified, efficient toolchain. Read the full article: {% endupdate %} {% update date="2026-03-16" %} ## W12 - D2 Observations: Front-End Vitality in the AI Wave From D2, this piece looks at how the role of front-end development is changing in the AI wave, and how front-end capabilities are moving toward more complete problem solving. Read the full article: {% endupdate %} {% update date="2026-03-09" %} ## W11 - Twitter’s Algorithm Evolution and Iteration in Source Management Using Twitter’s algorithm evolution as a lens, this piece discusses source management: the stronger the algorithm, the more important it becomes to actively filter and verify information sources. Read the full article: {% endupdate %} {% update date="2026-03-02" %} ## W10 - The Post-OpenClaw Era: The Coding Singularity Has Arrived, but New Production Relations Have Not Coding capability has made a leap, but organizational structures, incentives, and production relations have not changed in step. Read the full article: {% endupdate %} {% update date="2026-03-01" %} ## W09 - A Thinking Framework in Extreme Market Conditions When market sentiment turns extreme, use company culture, business model, independent thinking, and macro signals to cut through the noise, so judgments can be reviewed later and emotions do not erode the framework. Read the full article: {% endupdate %} {% update date="2026-01-25" %} ## W04 - What Is AI-Ready? AI-ready is not about chasing a specific model or tool. It is about establishing engineering standards that compound over time and naturally absorb progress in LLMs and infrastructure. Read the full article: {% endupdate %} {% update date="2026-01-18" %} ## W03 - Lessons from Troubleshooting Advanced Problems For difficult front-end problems, distinguish hidden code defects from uncertain runtime behavior: first use a workaround to contain the risk, then rely on long-term observation to get closer to the truth. Technical explanations are not always complete. Read the full article: {% endupdate %} {% update date="2026-01-11" %} ## W02 - Rethinking Complex Abstractions AI coding is pushing software engineering from an “economy of scarcity” toward an “economy of abundance.” Complex abstractions may no longer reduce costs; Tailwind’s dilemma also exposes how the old open-source model of monetizing attention is breaking down. Read the full article: {% endupdate %} {% endupdates %}