https://johnjwang.com/Recent content in Home on John WangHugo -- gohugo.ioen-usTue, 30 Jun 2026 00:00:00 +0000https://johnjwang.com/post/2026/06/30/why-we-built-143/Tue, 30 Jun 2026 00:00:00 +0000https://johnjwang.com/post/2026/06/30/why-we-built-143/The best person to understand a problem really deeply usually isn’t an engineer, it’s usually someone who’s using the product day in and day out with customers. Or it’s the customer support person who sees questions all day about why a particular feature isn’t working. While engineers have historically been the only people who could fix things, that’s not true anymore. Now with coding agents, non-engineers can fix things too and tend to be closer to the problems that users run into on a daily basis.https://johnjwang.com/post/2026/05/31/cheap-software-wont-make-engineering-cheap/Sun, 31 May 2026 00:00:00 +0000https://johnjwang.com/post/2026/05/31/cheap-software-wont-make-engineering-cheap/In a world where AI writes more and more of the code, is it crazy to still want to be a software engineer? My answer is no. I think there will still be a reasonably large number of engineers in the future, and some of them will be incredibly well paid. I’m not necessarily saying there will be more of them than there are today. But if you’re an engineer (or whatever the future version of the job ends up being called) and you know how to build high-quality systems that solve real needs, you’re going to be very valuable.https://johnjwang.com/post/2026/05/29/time/Fri, 29 May 2026 00:00:00 +0000https://johnjwang.com/post/2026/05/29/time/I’ve been thinking about time lately, especially how much of it is available. The strange thing I keep coming back to is that life feels both incredibly long and incredibly short at the same time, depending on which angle you look at it from. Both things can be true at the same time. It reminds me of the coastline paradox: a coastline wraps around a perfectly finite patch of land, yet the closer you measure it, the longer its edge gets, running off toward infinity the finer your ruler.https://johnjwang.com/post/2026/05/06/tokens-shouldnt-be-the-only-metric/Wed, 06 May 2026 00:00:00 +0000https://johnjwang.com/post/2026/05/06/tokens-shouldnt-be-the-only-metric/I’ve heard of a lot of teams recently starting to use number of tokens as the key metric by which they measure their engineering team. It’s actually kind of funny that I even feel the need to write this blog post, but I did want to get it on record: I think it’s a bad metric if it’s your primary north star. Should it be one of many metrics that you use to understand how people on your team are performing?https://johnjwang.com/post/2026/03/27/why-are-executives-enabled-with-ai-but-ics-arent/Fri, 27 Mar 2026 00:00:00 +0000https://johnjwang.com/post/2026/03/27/why-are-executives-enabled-with-ai-but-ics-arent/I think there’s pretty clearly a divide in AI perception between executives and individual contributors (ICs). Executives seem to love it and evangelize it (going so far as to creating mandates at their companies for AI usage). But ICs are typically much more skeptical of its usage. You can see the divide show up everywhere from Hacker News comment threads to internal Slack debates about adopting coding agents. Here’s my current posit for why there’s such a big divide: executives have always had to deal with non-determinism and focus on nondeterministic system design, while individual contributors are evaluated by their execution on deterministic tasks.https://johnjwang.com/post/2026/03/21/mamba-3/Sat, 21 Mar 2026 00:00:00 +0000https://johnjwang.com/post/2026/03/21/mamba-3/Mamba-3 just dropped yesterday. It’s a big milestone towards unseating the stranglehold that transformers have on the modern AI industry. Mamba-3 is a state space model, and it’s fascinating because it uses an entirely different architecture from transformers (the tech that the big LLMs like Opus 4.6, GPT 5.4, Gemini 3, etc. are based on). Transformers keep a huge memory layer called the KV cache: this essentially stores all the memory of everything previously said in a conversation when it is computing the next token.https://johnjwang.com/blog/Mon, 01 Jan 0001 00:00:00 +0000https://johnjwang.com/blog/I host most of my blog posts on Medium and the Assembled Blog (usually the engineering section of the blog). Here are some recent posts: 2026-06-30 Why we built 143 2026-05-31 Cheap software won’t make engineering cheap 2026-05-29 Time 2026-05-06 Number of tokens shouldn’t be the only metric 2026-03-27 Why are executives enamored with AI but ICs aren’t? 2026-03-21 Mamba-3 2025-10-22 Why I write code as a CTO 2025-08-05 Why blocking LLMs from your website is dumb 2025-06-01 Your LLM provider will go down, but you don’t have to 2025-04-08 How we learned to stop worrying and love the AI (in coding interviews) 2025-01-07 Scaling LLMs with Golang: How we serve millions of LLM requests 2024-10-24 How we saved hundreds if engineering hours by writing tests with LLMs 2024-05-28 Better RAG results with Reciprocal Rank Fusion and Hybrid Search 2023-08-30 How we built Assembled’s New Products Team 2023-06-30 Database abstractions for Golang 2023-06-16 Product lessons from Dan Robinson (ex-CTO of Heap) 2021-07-12 Applying Stripe’s lessons to Customer Support 2021-06-10 My startup journeyhttps://johnjwang.com/opinions/Mon, 01 Jan 0001 00:00:00 +0000https://johnjwang.com/opinions/I sometimes cringe at this part of my website (who cares about my opinions anyways), but I leave this up because back in college a similar “Opinions” section actually started some awesome conversations, so maybe it will in the future too. Stay somewhere long enough to see legacy code Most engineers change jobs frequently, but the best engineers I’ve known tend to stay somewhere for a long time. It can be difficult seeing your peers move to exciting, flashy companies with big salaries and titles, but I’ve found that staying in one place gives you deep wisdom and perspective.https://johnjwang.com/woodworking/Mon, 01 Jan 0001 00:00:00 +0000https://johnjwang.com/woodworking/Most of my woodworking creations can be found on doveandtail.com.https://johnjwang.com/work/Mon, 01 Jan 0001 00:00:00 +0000https://johnjwang.com/work/Here’s some of the stuff that I’ve worked on: Economics I spent many of my early years learning about and doing research in economics. I worked under Emily Oster (now a Professor at Brown) and Kerwin Charles (now the Dean of the Yale School of Management) to study the Black-White achievement gap. I also assisted with Robert J. Gordon’s book “The Rise and Fall of American Growth”. I focused my research on the quality of American housing between 1870 and 1930.