Often the smartest thing is to do nothing.
Or know when to shut up.
A tangent, but can anyone ELI5 how models "know" when to stop generating tokens? Or what the method to stop them at the right point is?
alt Hacker News
Or know when to shut up.
A tangent, but can anyone ELI5 how models "know" when to stop generating tokens? Or what the method to stop them at the right point is?