blog

Over the past three years at Val Town we've been copying the best AI coding tools (and occasionally getting copied ourselves!). We've riffed on ChatGPT, Claude Artifacts, GitHub Copilot, Cursor, Windsurf, ..., and most recently Claude Code. At one point we even rewrote Townie entirely in user space, 100% open source.

We've done five throw-away-the-code-and-start-from-scratch rewrites:

• v1: ChatGPT-inspired
• v2: ChatGPT-inspired, with tools
• v3: Claude Artifacts-inspired
• v4: Open source, in "user space"
• v5: Claude Code-inspired
• v6? More on that in a minute

Some of those versions felt like the bell of the ball while others were just ok. The through line is that we feel good about investing in timeless developer principles and tools—the AI will find its place. Five rewrites in, this is the story of why it's all worthwhile.

Before founding Val Town in July 2022, I ran the Future of Coding podcast and community. Boy, were we completely blindsided by AI. We didn't predict or invent the future of coding at all!

But I'm not an AI hater. I'm actually quite into it. My fiancé jealously calls ChatGPT my "girlfriend." If we were fundraising right now, I might feel short-termist pressure to lie through my teeth telling you how Val Town "was founded to reimagine what computing could be with AI." But I don't have to! Because the whole point of AI devtools are to multiply your powers as the programmer working on the code. And we built Val Town for you the programmer and your code. AI just fits in naturally.

Jeff Bezos said he could afford putting lots of effort into things that won't change in 10 years. He knew Amazon customers would always like lower prices and faster shipping, just like we know that you will always like 100ms or faster deployments and lower infra setup costs.

At Val Town we center on timeless principles that won't change in 10 years and create timeless tools to realize those principles. We care about:

• Joy
• Immediacy
• Code-first
• Collaboration
• Open technology

This one is the most important to me. Programming is, and should be, incredibly fun. This is why we build Val Town: to spread the joy of programming. Like how Matz designed Ruby to make programmers happy.

Coding on Val Town grants you "an immediate connection to what you're creating," as Bret Victor would say. Tight feedback loops, as I often say. Save, 100ms deploy, live URL. Programming in Val Town should feel like editing a spreadsheet, where you hit enter and everything recomputes instantly.

We think that the code itself still matters and that you should understand it. This may be somewhat contrarian these days with the industry's embrace of vibe coding and agents working for you while you cook dinner, do laundry, and sleep. Vibe coding has its place, but remember: vibe code is legacy code, which means it's great for low-stakes code and code you don't have to maintain but not good for your enduring, important code.

When we wrote about copying all the best code assistants a year ago, the top Hacker News comment by ajhit406 posed the question of who Val Town is for:

One consideration not mentioned is around developer sophistication. Steve alludes to the expansion effect of CodeGen ("there are millions and maybe billions who are jumping at the chance to code"), but doesn't consider that the vast majority of these people don't know about arrays, data structures, memory, containers, runtimes, etc, etc...To me, that's the most important consideration here. Are you targeting professional devs who are enhancing their current workflows iteratively with these improvements? Or re-thinking from the ground up, obfuscating most of what we've learned to date?

It's the right question, and the answer has two parts:

1. Our moonshot mission is end-user programming. That's for the "millions and maybe billions" who should have full power to shape their software like programmers do today. But we're not starting with that...
2. For now, we are working toward end-programmer programming. That means "targeting professional devs who are enhancing their current workflows iteratively," to use ajhit406's words exactly

Embracing code-first gives you the programmer full power—complete flexibility over what you're building. But it should not mean a high learning curve or complexity. Spreadsheets are simple enough that a beginner can create something useful (say, a budget) within an hour, yet powerful enough that experts can create endlessly sophisticated models over hundreds of hours. Like spreadsheets, coding in Val Town should be simple and joyful, yet endlessly powerful.

...

We believe in making long-term bets on open standards/tools and supporting open source. Val Town code runs on the open-source Deno runtime, our in-browser editor uses CodeMirror (which we contribute back to from time to time), and we rely on countless other open tools like SQLite and esm.sh.

The pace of Al is so blisteringly fast that it's proven easier to throw out all our code every six months. AI is changing devtools along two dimensions:

1. LLMs keep getting better: smarter, faster, cheaper
2. We as an industry keep finding better form factors: tab completions, tool use, agent loops

It's hard to predict how programmers will want to code a month from now. The pace of change makes it incredibly hard to invest deeply in any one approach, and this is doubly true for a seed-stage startup like us.

Before building Townie v5, our intention was to thoughtfully craft a good MCP server so that you can stay where you are (in your favorite AI coding tool). But MCP clients just aren't good enough yet, so we built our v5 in-browser coding bot on top of our MCP server. I would love for the AI labs to realize that in addition to Consumer and API companies they are also Platform companies. I want them to take this responsibility and opportunity seriously and invest in a proper "App Store." We could focus on building the best coding platform while the AI providers handle the AI things — billing, rate limiting, combating abuse, etc.

So will we throw away the code and rewrite Townie again in 6 months? Yes, probably. And it will continue in our tradition of fitting together our favorite AI coding patterns of the moment with Val Town's timeless principles.

Thanks to my "speechwriter" Pete for helping me write this.