Synthèse
The quality of prompts matters more than model choice, RAG, or fine-tuning. "90% of AI's power is in prompting—NOT RAG, NOT fine-tuning, NOT even the models themselves."— AI is Mostly Prompting, May 2024 Analysis: I'll take a victory lap on this one. People spent 2024 chasing RAG and fine-tuning, and now in late 2025 everyone's re-discovering that prompting (now called "context engineering") is where the leverage actually is. IBM's 2025 guide states: "Prompt engineering is the new coding." I sai
The quality of prompts matters more than model choice, RAG, or fine-tuning. "90% of AI's power is in prompting—NOT RAG, NOT fine-tuning, NOT even the models themselves. "— AI is Mostly Prompting, May 2024 Analysis: I'll take a victory lap on this one. People spent 2024 chasing RAG and fine-tuning, and now in late 2025 everyone's re-discovering that prompting (now called "context engineering") is where the leverage actually is. IBM's 2025 guide states: "Prompt engineering is the new coding.
" I said this in May 2024 and got pushback. Now it's consensus. VERDICT: Called it—and people are finally catching up.
Source originale
danielmiessler.com
Personalization > Prompting
· 26 juil.