This goes for almost all AI language models that I’ve used.
I ask it a question, and instead of giving me a paragraph instantly, it generates a response word by word, sometimes sticking on a word for a second or two. Why can’t it just paste the entire answer straight away?
In: Technology
Because that’s exactly how it works. LLMs are, at an extremely basic level, playing “guess the next word” based on a giant archive of text data.
Latest Answers