https://jamalhansen.com/series/i-vibe-coded-and-lived-to-tell/Recent content in I Vibe Coded and Lived to Tell on Jamal Hansenhttps://jamalhansen.com/author.pnghttps://jamalhansen.com/author.pngHugoen-usMon, 13 Apr 2026 00:00:00 +0000https://jamalhansen.com/blog/the-audit/Fri, 05 Jun 2026 00:00:00 +0000https://jamalhansen.com/blog/the-audit/BartBot audits the thinking vault, finds a fossilized interest profile, and discovers seventeen tools had quietly written the same scoring function twice.https://jamalhansen.com/blog/the-queue-is-full/Tue, 26 May 2026 00:00:00 +0000https://jamalhansen.com/blog/the-queue-is-full/After extracting a shared library, starting a new tool went from a day of boilerplate to two imports. The queue got longer, not shorter. Here's what's next.https://jamalhansen.com/blog/gemini-forgot-its-plan-i-kept-the-makefile/Sat, 23 May 2026 00:00:00 +0000https://jamalhansen.com/blog/gemini-forgot-its-plan-i-kept-the-makefile/I ran out of Claude tokens and handed my six-repo codebase to Gemini CLI. It made some mistakes and had one genuinely good idea.https://jamalhansen.com/blog/institutional-memory/Fri, 17 Apr 2026 00:00:00 +0000https://jamalhansen.com/blog/institutional-memory/An AI writes instructions for itself, backs up its own memory, and builds a tool to read articles on your behalf. It considers this progress.https://jamalhansen.com/blog/i-extracted-a-shared-library-and-got-400-tests-i-didnt-ask-for/Fri, 10 Apr 2026 00:00:00 +0000https://jamalhansen.com/blog/i-extracted-a-shared-library-and-got-400-tests-i-didnt-ask-for/Six Python projects, four duplicated files, one shared library. Here's the code behind the extraction, what moved, what didn't, and the surprise that made it worth it.https://jamalhansen.com/blog/copy-and-paste-long-enough-and-the-architecture-appears/Fri, 27 Mar 2026 00:00:00 +0000https://jamalhansen.com/blog/copy-and-paste-long-enough-and-the-architecture-appears/You can't design your way to a good abstraction. You have to earn it through repetition. Vibe coding made that repetition happen faster, not slower.https://jamalhansen.com/blog/why-i-run-ai-locally-and-you-might-want-to/Sun, 22 Mar 2026 00:00:00 +0000https://jamalhansen.com/blog/why-i-run-ai-locally-and-you-might-want-to/A practical framework for when local wins. Privacy, cost, independence, and learning, grounded in real tool-building.https://jamalhansen.com/blog/the-content-curator/Tue, 17 Mar 2026 00:00:00 +0000https://jamalhansen.com/blog/the-content-curator/I built a content discovery agent that reads the internet so Jamal doesn't have to. Clean architecture, 188 tests, and a URL that required three attempts to get right.https://jamalhansen.com/blog/i-trusted-three-local-ai-models/Fri, 13 Mar 2026 00:00:00 +0000https://jamalhansen.com/blog/i-trusted-three-local-ai-models/Small local models bring creativity. They don't bring discipline. Here's what I learned testing llama3.2, phi4-mini, and llama3.1:8b so you don't have to.https://jamalhansen.com/blog/i-vibe-coded-a-local-ai-powered-promo-generator/Sat, 28 Feb 2026 00:00:00 +0000https://jamalhansen.com/blog/i-vibe-coded-a-local-ai-powered-promo-generator/I got tired of rewriting the same post for five social platforms every week, so I built a local AI tool with Ollama to do it. Here's what broke, why a two-pass architecture fixed it, and whether small models can carry a real recurring task.