Improving LLM chatbot UX by utilizing a stateful Markdown stream processor

Y	Hacker News new \| ask \| show \| jobs

	Improving LLM chatbot UX by utilizing a stateful Markdown stream processor (shopify.engineering)
	4 points by atesgoral 1037 days ago

1 comments

russellbeattie 1037 days ago

Or you can specify that LLMs respond in valid HTML and save yourself the processing step.

link

atesgoral 1037 days ago

Ignoring the additional token count cost of HTML, how do you envision rendering HTML that is spit out by an LLM directly (without any processing) to the user?

link