Improving LLM chatbot UX by utilizing a stateful Markdown stream processor

Posted by atesgoral on Wednesday August 16, 2023 @01:12PM
from the shopify.engineering dept.

https://shopify.engineering/sidekicks-improved-streaming

( 2 comments | 3 points | on HN )

Re:Improving LLM chatbot UX by utilizing a stateful Markdown... by russellbeattie on Wednesday August 16, 2023 @02:17PM (#37151326)

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

[ Parent | on HN ]

Re:Improving LLM chatbot UX by utilizing a stateful Markdown... by atesgoral on Wednesday August 16, 2023 @05:59PM (#37154452)

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?

[ Parent | on HN ]