Hacker News new | ask | show | jobs
by russellbeattie 1039 days ago
Or you can specify that LLMs respond in valid HTML and save yourself the processing step.
1 comments
atesgoral 1039 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