LLMs are a really accessible machine learning technique. I dabbled with text classifiers a few years ago and the APIs were way more involved.
(system_prompt: String, input: String) -> String
I can prototype with this much more easily!
miniblog.
Related Posts
I'm writing a Path type in my programming language but not sure what methods belong on a Path.
Should I have some_path.read_string() or fs::read_string(some_path) instead?
I love .method() for IDE completion, but I don't want Path to be cluttered. I'm also trying to avoid UFCS.
What's the best string representation of a function? Comparing with other PLs:
Python: <function __main__.add_one()>
JS: [Function: addOne]
Clojure: #function[user/add-one]
Scheme: #<procedure add-one (x)>
I'm currently thinking about <fun add_one() foo.gdn:123>
I've been iterating further on how Garden shows type errors.
For types in the standard library, I'm now showing "a String" but "an Int". I'm also doing basic syntax highlighting of the code excerpt.
What do you think?