Yes that’s the case. And as Anthropic staff, author has an incentive to promote workflows that require an agent to interact with text documents.
I've yet to see Anthropic promote any sort of token optimization strategy to its users - they always assume we all have infinite inference.
"No bread? Let them eat cake!"
HTML is by far simpler than Markdown.
I've yet to see Anthropic promote any sort of token optimization strategy to its users - they always assume we all have infinite inference.
"No bread? Let them eat cake!"