DeepMind researchers detail Optimization by PROmpting to improve LLM performance by using “meta-prompts” like “take a deep breath”, which helped Google's PaLM 2 (Benj Edwards/Ars Technica) 20-09-2023
Benj Edwards / Ars Technica: DeepMind researchers detail Optimization by PROmpting to improve LLM performance by using “meta-prompts” like “take a deep breath”, which helped Google’s PaLM 2 — DeepMind used AI models to optimize their own prompts, with surprising results. Lees verder op Tech Meme