LLM / local model "vibe coding"
Last week I set my local LLM to do it's first mission where it vibe coded some integration tests for me. I added a "allow local file edits" mode to my harness a little while ago but I hadn't had time to actually give it a go. I spent some time as I was logging off work to go on a date to make a plan with the LLM to test some changes to our replication code and gave it some constraints on which shell tools it'd be auto-allowed to use and set it off.
LLM / local model "vibe coding"
I'm not sure how long it was chugging away at it, but I see in the logs that it did a few iterations and some bug fixing as it went along. The final code looks pretty much how I would have done it. I don't think this means I'll be using this feature daily, but I might give it another shot next time I have a concrete plan that I want to execute while I make dinner or whatever.
LLM / local model "vibe coding"
Also! It ended up creating race conditions due to attaching listeners at the wrong point in the test (which didn't matter for this case) but I think I can modify the project's AGENTS.md to make sure it doesn't make the mistake a again.