Coding Posts

I cloned GitHub. Not a toy demo with three screens and a README viewer -- a full-featured, single-user Git hosting platform with repository management, code browsing with syntax highlighting, pull requests with three merge strategies, issues with labels and comments, releases, search, activity feeds, insights, dark mode, and 50+ API endpoints. 111 files. 18,343 lines of code. 155 passing tests. The whole thing took 49 minutes, entirely within the scope of a Claude subscription.

Day three. Another SaaS subscription, another Single Serving Application. I've now replaced Harvest (time tracking) and Trello (project management) with AI-generated clones. Today's target: Confluence -- Atlassian's knowledge management and wiki platform. Claude Opus 4.6 built a fully functional Confluence clone in 16 minutes, consuming 106,000 tokens. That's the fastest build yet -- down from 18 minutes for Harvest and 19 for Trello. The pattern is holding: requirements in, working application out, no human intervention needed.

Last week I had Claude Opus 4.6 and GPT-5.3-Codex race to build a Harvest clone. Claude won decisively. That experiment killed a $180/year SaaS subscription. Naturally, I started looking at my other subscriptions. Trello was next on the list. I've used it for years to manage personal projects, product roadmaps, and random ideas. It's a great product -- but it's also a multi-tenant, collaboration-heavy platform where I use maybe 20% of the features. A perfect candidate for a Single Serving Application. So I wrote a requirements document, handed it to Claude Opus 4.6, and walked away. 19 minutes and 137,000 tokens later, I had a fully functional Kanban board running on localhost.

I recently had two AI models build a complete Harvest clone in under 20 minutes. The winning version covered 97% of Harvest's features. I'm seriously considering canceling my $180/year subscription and using it instead. That experiment got me thinking about something bigger than one app replacement. We're entering an era where a competent engineer with an AI coding assistant can generate a fully functional web application from a requirements document in the time it takes to eat lunch. That changes the economics of software in a fundamental way.

Last week was a big week for Anthropic and OpenAI. Both released new versions of their flagship coding models: Claude Opus 4.6 from Anthropic and GPT-5.3-Codex (Medium) from OpenAI. Any time new coding models are released, it's like an extra Christmas for me. There was some talk about Sonnet 5.0 being released also but so far, nothing. I'm wondering if that has anything to do with the most recent agentic coding benchmarks.

Recently, I failed one, probably two, maybe even three, live coding exercises. The exercises were part of a series of interviews for a role at a startup that makes products and services I'm passionate about. I've written a different article about my thoughts on the value of live coding exercises but wanted to take this opportunity to narrate my lifetime of experience writing computer code. I don't expect this article to be of any interest to anyone, save perhaps a future interviewer, in which case I hope this lends some credence to the statement "I know how to code."