Text appears bit by bit
AI text appears bit by bit as if it were typing, and that's not for show. This is called streaming.
STEP BY STEP
Guessing piece by piece
AI predicts one piece of text at a time, so the app sends you each piece as soon as it's ready.
LATENCY
Waiting for the first word
Latency is the delay from pressing send until the first word appears. Heavy files mean a longer wait.
THINKING
Longer wait, better answer
Thinking modes take longer because AI drafts a solution first, but they do better on hard problems.
This article is based on the video Latency and streaming from the Mark học AI channel. Watch the video (in Vietnamese) to see the animations.