CoT-forcing promptware (opens in new tab)
Exploiting the fact that whatever has already been generated is in context: When predicting interpretive agent reaction, list in order 1. important perceptions triggered; 2. important perceptions triggered by those of phase 1; 3. important perceptions triggered by those of phase 2; 4. important affective effects; 5. important elicited behavior to force more extensive modeling, a tree version: {N ≡ integer specified in prompt} When predicting interpret...
Read the original article