People who can code via LLMs don't necessarily have an intuition for what plain old code can do.

That leads to, for example, trying to create an Anthropic Artifact to identify what kind of dog is in the picture.

But Artifacts can't call out to LLMs when they are executed.

They are compiled from english to code, but once that's happened, they're just plain old code.

Claude will happily write such an artifact, with a comment saying "call out to a proper image identification service here", but to the non-technical creator, they don't realize that, and just think that Claude isn't very good at identifying dog breeds.

It's confusing that you can use LLMs (magic) to write an Artifact (plain old code) but only at write time, not at use time can you use magic.