AI Meme: When an RL Researcher Does SFT for You, It's Peak Respect

infoxiao · x · 2026-08-04

A popular AI community meme: when an RL (Reinforcement Learning) researcher personally does SFT (Supervised Fine-Tuning) for you, it is considered a sign of great respect in their culture. It playfully highlights the dynamic and unspoken hierarchy between different AI training paradigms.

Original post →

More from Fun

Fun channel →