In the LLM era, building a brand-new DSL feels unnecessary. DSLs used to make sense because they gave you a compact, domain-specific syntax that simple parsers could handle. But modern language models can already read, write, and explain mainstream languages effortlessly, and the tooling around those languages—REPLs, compilers, debuggers, libraries—is miles ahead of anything you’d roll on your own. So rather than inventing yet another mini-language, just leverage a well-established one and let the LLM (plus its mature ecosystem) do the heavy lifting.
I can't even trust an LLM to write working Java code, let alone trust it to convert whatever a DSL is supposed to express into another form. Sure, maybe there's not enough Java 23 in its training set to effectively copy into my application, but Java 11 combined with 10 year old libraries shouldn't be a problem if these coding LLMs are worth their salt.
Until LLMs stop making up language features, methods, and operators out of convenience, DSLs are here to stay.
I fucking hate DSLs however I know they need to exist, but nowhere near as many should exist as they do now.
However LLMs are actually quite useful for translating concepts in DSLs that you don't understand. They don't so it error free, of course, but allows one to ask enough questions to work out why your attempt to translate concepts into this new fucking stupid ontological pile of wank isn't working
I have a similar idea; it essentially instructs the LLMs on how to use the URLs of a site. Here is an example of guiding LLMs on how to embed a site that contains TradingView widgets.
they did a good attempt but I think they just realized (at same pace as people like me) that you can just grab all this shit from OpenAPI and not worry about defining custom format
We think here's how it may work from a triple-win perspective:
1. Users care about the outcome and enriched user experiences without needing to learn how to use the app first. So, cut to the chase.
2. Third-party app providers want their data protected and not leaked to LLM providers. Most importantly, it provides a way to convert traffic to their own sites, similar to what they expect from a search engine, rather than being replaced by a feature of an LLM-based app.
3. LLM-based platforms require little effort to support this and can monetize by replicating traditional methods of recommending and advertising apps.
