Is prompt engineering dead? No, it’s SoTA. GPT-4 with good prompts (dynamic k-shot + self-generated CoT + choice-shuffled ensembles) beats Med-PaLM 2 on all nine of the MultiMedQA benchmarks it was fine-tuned for, without fine-tuning:
GPT-4 with good prompts beats fine-tuned Med-PaLM 2
By
–
