Re:Show HN: Runner – the anti-vibe coding agent
by zmccormick7 on Thursday September 11, 2025 @06:26PM
(#45216741)
I agree that's a major problem. It's not something I've solved yet. I suspect a web research sub-agent is likely what's needed, so it can pull in up-to-date docs for whatever library you need to work with.
Re:Show HN: Runner – the anti-vibe coding agent
by evelant on Friday September 12, 2025 @07:53AM
(#45221144)
I’ve largely solved this with the context7 mcp server. Any time my prompt is likely to touch apis I know the LLM will get wrong I tell it to review the docs with context7 first.
Re:Show HN: Runner – the anti-vibe coding agent
by zmccormick7 on Friday September 12, 2025 @10:10AM
(#45222344)
Good to know. I've heard great things about Context7, but haven't experimented with it yet.
A persistent issue I have with Cursor et al. is that they hallucinate function arguments when using a function or method from a library. It seems like automatically pulling the library's documentation into the context would be helpful, but I haven't found any tool that does this automatically. Is there any chance that Runner does this?
It doesn't seem like this was the problem you were trying to solve, but reliable use of libraries and APIs is a critical problem to solve if you want LLM-generated code to work.