Comment by modeless
2 years ago
You're right, the models do think non-verbally. However, crucially, they can only do so for a fixed amount of time for each output token. What's needed is a way for them to think non-verbally continuously, and decide for themselves when they've done enough thinking to output the next token.
Is it clear that humans can think nonverbally (including internal monologue) continuously? As in, for difficult reasoning tasks, do humans benefit a lot from extra time if they are not allowed internal monologue. Genuine question