AI Dynamics

Global AI News Aggregator

About

Few-shot Prompt Setup Notes for Scaling Law Experiments

Some setup notes (cc @EthanJPerez
) – We used the exact 2-shot prompt for Quote Repetition, which is already U-shaped for Gopher/Chinchilla – We used fewer shots for Hindsight – We did few-shot instead of 0-shot for Negation QA – We also showed inverse scaling up to PaLM 62B

→ View original post on X — @_jasonwei,