{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"YAGNI","title":"LLM junk food w/ Justin Duke","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/c11d83ab\"></iframe>","width":"100%","height":180,"duration":3514,"description":"Justin Duke, who runs Buttondown, calls himself a \"radical LLM centrist.\" About two-thirds of Buttondown's merged code comes from LLMs, but he still pushes back on the most extreme software factory takes. He and Matt talk about why most \"factories\" are only tuned for throughput and why so much agent work is snacking: low effort and low value. They also get into the rise of fake third-party services, and whether Kanban is a warning about borrowing manufacturing ideas without the principles behind them. Plus: a huge pile of regexes, CI that rejects PRs without screenshots, and why Buttondown's Storybook has quietly become its staging server.\nMentioned in this episode\nSnacks are cheaper and tastier than ever: Justin's post on how LLMs make low-effort, low-value work very tempting. You get the rush of 15 merged PRs and no effect on customers. It pairs well with his Be careful what you make easier.\nPlanetScale's self-improving database: Both teams feed PlanetScale's Insights and schema recommendations to agents that open PRs, some of which merge automatically. It's close to a free lunch, though Justin argues it's also where the factory metaphor breaks, since real factories don't improve themselves.\nLinear Customer Requests: Justin's favorite little-used Linear feature. You link issues to customers along with their revenue, so \"who's asking for this, and does it change whether they churn?\" gets answered before an agent starts on the backlog.\nPlain: Buttondown's support tool. Instead of sending every thread to an LLM classifier the way Plain would like, they use a \"staggeringly terrifying\" pile of regexes that's easy to improve over time. Matt's team went the same way, with LLMs writing the regex instead of being the classifier.\nStrongDM's Digital Twin Universe: This is the software factory's take on the manufacturing \"digital twin.\" StrongDM had agents build clones of Okta, Jira and Slack from their public API docs so they could run thousands of test scenarios an hour....","thumbnail_url":"https://img.transistorcdn.com/UMMB8JkX91ih6GoZqlbBWDXY7T-jmGQ8Ufj2jHpLxMw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9zaG93/LzMyODAyLzE2NTk0/MDE1MTYtYXJ0d29y/ay5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}