Field notes from the frontier of AI and 3D printing — reviews, prints, local-LLM guides, prompts and editorials.https://lvl30.com/enhttps://lvl30.com/news/welcome-to-the-respawn/https://lvl30.com/news/welcome-to-the-respawn/The site respawned, retooled for AI and 3D printing. What's launching, how often, and what the streams are all about.Sun, 07 Jun 2026 00:00:00 GMTNewsmetaannouncementAndrewhttps://lvl30.com/prints/week-01-gridfinity/https://lvl30.com/prints/week-01-gridfinity/Start here. Gridfinity turns a messy desk drawer into a smug, modular grid — and it's the perfect first 'useful' print to dial in your printer.Sat, 06 Jun 2026 00:00:00 GMTPrint of the Week3d printinggridfinityorganizationplaAndrewhttps://lvl30.com/reviews/bambu-lab-h2d/https://lvl30.com/reviews/bambu-lab-h2d/Two weeks of near-silent, hands-off printing. The H2D is fast, frighteningly consistent, and the closest thing yet to a print-and-forget machine — if you can stomach the ecosystem lock-in.Fri, 05 Jun 2026 00:00:00 GMTReviews3d printinghardwarebambu labfdmAndrewhttps://lvl30.com/guides/your-first-local-llm-with-ollama/https://lvl30.com/guides/your-first-local-llm-with-ollama/No cloud, no API key, no data leaving your machine. A genuinely beginner-proof path to running a capable model locally — plus how to know which size your hardware can actually handle.Thu, 04 Jun 2026 00:00:00 GMTLocal LLM Guidesailocal llmollamaprivacyAndrewhttps://lvl30.com/reviews/how-i-test-frontier-models/https://lvl30.com/reviews/how-i-test-frontier-models/Benchmarks are marketing. Here's the repeatable, boring, real-work gauntlet every new frontier model runs through before it earns a number on lvl30 — and why most of them land between 7 and 8.Wed, 03 Jun 2026 00:00:00 GMTReviewsaillmmethodologyfrontier modelsAndrewhttps://lvl30.com/prompts/the-rubber-duck-refactor/https://lvl30.com/prompts/the-rubber-duck-refactor/The single highest-leverage prompt I use. It forces the model to understand code before changing it, which kills the confident-but-wrong rewrites that waste your afternoon.Tue, 02 Jun 2026 00:00:00 GMTPrompts That WorkaipromptscodingrefactoringAndrewhttps://lvl30.com/editorials/ai-wont-replace-makers/https://lvl30.com/editorials/ai-wont-replace-makers/The doom take and the hype take are both lazy. After a year of using AI elbow-deep in real projects, here's the actually-interesting middle: the tools are eating the toil, not the craft.Mon, 01 Jun 2026 00:00:00 GMTEditorialsaieditorialmakingfutureAndrew