Contradictory anecdote: there’s basically only one way to write Elm, as it is a very trend-resistant language with minimal updates over long timespans, but most agents in my experience will throw Haskell syntax and Prelude functions into their Elm output. Compiler or LSP will often set them right but they still try it initially

I do agentic Elm development every day (it's my job). I feel like what you describe was a problem with models perhaps two years ago. Today's models don't seem to struggle with it at all and in fact do seem to benefit from what the author describes.

I’ve just started a new app with an Elm frontend. I’m using Grok Build, and it integrates really well.

The compiler is incredibly helpful because it catches errors and gives clear explanations and the LLM can iterate over it. I’ve also added the elm-review package with the default configuration, which is fantastic for ensuring code quality.

Interesting, what models are you using? My use with sonnet 4.6 has been a breeze for the most part

Interesting, I have a different experience.

I have worked extending the Elm compiler and both Opus 4.6, GPT 5.4 and GLM 5 had no issues both with the Elm compiler (written in Haskell) and my extended Elm.

I didn't see them hallucinate much, not more than on mainstream languages.