1,742
1,740
1,7371,7371,7361,7361,736495495
435431314314
1881d ago · 3 min read · Problem Parallel AI coding feels magical until both agents start maintaining their own version of reality. One agent remembers a rule from chat history. The other reads a repo note that is already stale. A workflow gets updated in one place but not t...
Join discussion2d ago · 5 min read · Six weeks ago I started building bombop, an AI dance video generator. Not a research toy — something a TikTok creator could open at 11pm, drop a photo into, and have a finished clip by midnight. This post is the unfiltered version: what worked, what ...
Join discussion3d ago · 3 min read · Building Crompty From Nothing: The Silent Struggles Behind an Independent Startup Most people only see a finished website. They visit a platform, scroll a few pages, maybe sign up, maybe leave. What t
Join discussionApr 22 · 8 min read · Originally published on rollgate.io/blog/ab-testing-feature-flags. Why A/B Test with Feature Flags? Most teams think A/B testing requires a dedicated experimentation platform — Optimizely, LaunchDarkly Experimentation, or Google Optimize (RIP). Thes...
Join discussion
Apr 19 · 3 min read · The SLO Translation Problem You define an SLO: 99.95% availability with p99 latency under 200ms. Engineering loves it. Product managers glaze over. The problem isn't the SLO. It's how we communicate it. Speaking Product Language Translate technical S...
Join discussion
Apr 14 · 7 min read · I spent two days struggling with a small tool that just wouldn't work. Last January, I tried Claude Code for the first time. I had it hooked up to Kimi's model and wanted to build a browser extension. Every time it said "done," it wouldn't actually w...
Join discussionApr 14 · 6 min read · Recently, I've been working intensively with coding agents, and I made a surprising discovery. AI excels at getting things to 80% or even 90%. Give it a task, and it quickly produces something that looks good. But "looking good" isn't the same as bei...
Join discussionApr 14 · 7 min read · I spent two days struggling with a small tool that just wouldn't work. Last January, I tried Claude Code for the first time. I had it connected to Kimi's model and wanted to build a browser extension. Every time it said "done," I'd test it and it wou...
Join discussionApr 13 · 17 min read · This is the twentieth post of a course about AI product work, and it is the last. If you have read the previous nineteen in order, you have spent roughly 70,000 words of reading building a set of frameworks, decision rules, and skeptic kits for shipp...
Join discussion
