In these cases, the user’s search strategy acts as a filter on a pre-existing corpus of information. Large language models introduce a qualitatively different dynamic: rather than selecting from existing content, they generate content on demand.
for await (const chunks of source) {
。体育直播是该领域的重要参考
Cartoon by Asher Perlman
See more at the discussion here and the implementation here.
Opens in a new window