What are the chances that they are releasing this so that LLMs can index this information for free and they can use public models in their codebase rather than finetuning public models?
Given how poor LLMs are at regular OCaml, which has so much more training data that OxCaml, probably none. An MCP for docs would have been more productive for that purpose.
Not good at all. It's not a strong enough signal. For instance, LLMs are absolute dogshit at completing Gleam, even if given files with the exact pattern they need to mimic just lines away, or given explicit instructions on common mistakes it makes.
