Learnings from an Ex-Amazon Engineer
There are often moments when I can’t tell if LLM over-engineered, and that’s when I know I have limited knowledge on the subject. I rely a lot more on seniors and talking to models to learn here.
Most of this month I’ve been working on a contract AI-engineering project, I implemented sign-in-with-apple, iOS in-App purchase, sign-in-with-wechat (OAuth), account linking, revamped some UI/UX on iOS app; submitted the iOS app to App Store Connect and resolved four review cycles; I also surveyed, selected cloud vendors and migrated existing backend and database servers from HongKong to Beijing.
When designing systems, optimize for what we actually care about#
It’s all about identifying what we care most about and system engineer towards that. Systems engineering is about asking, at each step, how our decisions are helping us get to what we care about. In our case, we want to ship it quickly and get done with it, but we also want to be able to maintain it easily after our development. So Leo and I had lots of discussions around how to better design the database schema and related system (dev/prod env). Being able to identify tradeoffs for each decisions becomes even more critical.
Read what the LLM wrote#
You can’t skip reading what LLM coded, otherwise prepare for spaghetti code. Almost always, claude will over-engineer and make the codebase a lot harder to understand. Always be ready to ask if it over-engineered. There are often moments when I can’t tell if it over-engineered, and that’s when I know I have limited knowledge on the subject. I rely a lot more on seniors and talking to models to learn here.
Doc‑driven coding#
Engineering is changing from code driven to doc driven. For each feature you want to add, have LLM do research in the codebase and solution space and ask for a plan, then you have another agent code it out. You still need to understand what’s happening under the hood to make sure it’s not trying to end humanity. A very helpful way to do that is to have LLM create an ascii chart representing how the components work together, or sequence diagrams of how the threads are working at the end of each coding session. If it’s complex also have another vendor’s agent check it. Our current practice is to create a doc that has both ascii charts for human readability and file paths, function names in the descriptive paragraphs for LLM grepability. There is a trend of preparing data for LLM other than for human, not confusing them is one of the hard tasks.
I also imagine there will be tools that help you visualize & plan in the codebase in a more interactive and dynamic way in the near future (for high-level planning, building), more suited for LLM-driven (doc-based, abstracted) engineering.
Biggest blockers aren’t code anymore#
In the past month, the biggest blockers in product development usually aren’t technical, but approval bottlenecks. To login with an 2FA-enabled enterprise accounts might take minutes to hours, getting verified on the Weixin Open Platform involved almost a week of back-and-forth, and clearing App Store Connect required four review cycles, adding nearly another week of delay.
Git is still very important.#
Know your git commands, esp. when you git pull origin main, otherwise you’ll ended up introducing +10,000 -9,876 lines of code changes to your feature branch haha (when not rebasing well).
Yes, junior software engineer is not a thing anymore.
More in Startups
過去兩個月打造產品所學
相信自己,然後穩步前進
在 startup 工作 6 個月
作為一個對做酷東西和做產品感興趣的人而言,在一家優秀的新創公司實習是一件很幸運的事。一方面是因為能與很強的人共事,可以學到他們的心法以及做事方法論,另一方面是因為新創公司速度快、人少的特性,讓我有機會接觸到一些我現在能力範圍外的任務 (punch above my weight)。這篇文章主要寫的是這幾個月對專注的新理解,以及在 AI 時代做技術工作的一感想。
在 startup 工作 1 個月
最重要的是明確最重要的是什麼
敢於嘗試,機會是主動拿到的。
Get new posts by email, or via RSS.