Improving LLM chatbot UX by utilizing a stateful Markdown stream processor (shopify.engineering) 4 points by atesgoral 2y ago ↗ HN
[–] russellbeattie 2y ago ↗ Or you can specify that LLMs respond in valid HTML and save yourself the processing step. [–] atesgoral 2y 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?
[–] atesgoral 2y 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?
2 comments
[ 3.0 ms ] story [ 18.5 ms ] thread