"If there's one thing I want you to take away from this article, it's this: testing harness is the most important thing for vibe-coding. Not prompt engineering, not fancy plugins, just constraining your AI outside AI toolchain. I'm calling it harness because it's not only tests. It's tests, types, linters, and any other automated checks you can put in place. The more you rely on AI, the more harness you need."
"Scala 3 syntax works without issues. Same with implicits, type-level programming, and macros. Cross-compilation between JVM and JS? No problems. sbt? Also fine. I asked it to learn Laminar from the docs and it found Waypoint on its own without any struggle. I've thrown obscure libraries at it like decisions4s and it handles them pretty well. Having checked-out sources around helps but isn't necessary - it just goes to docs or GitHub if it doesn't know something."
Fifteen years of programming experience includes five years on mission-critical finance software. Two months of full-time AI-assisted coding were applied across personal projects, open-source work, and professional tasks. Agentic coding started around the Junie release (May 2025) with mixed results until tools improved significantly in December. Claude Code is now the primary tool, Junie is used occasionally, and Codex proved subpar. AI handles Scala 3 features, implicits, type-level programming, macros, cross-compilation (JVM/JS), sbt, and obscure libraries, often consulting docs or GitHub when needed. A testing harness of tests, types, linters, and automated checks is critical because AI tends to reason locally and can miss system-level issues.
Read at Medium
Unable to calculate read time
Collection
[
|
...
]