I’d argue that tokenization is more analogous to having a losslessly encoded ima...

		bertday on March 30, 2023 \| parent \| context \| favorite \| on: Cerebras-GPT vs. LLaMA AI Model Performance Compar... I’d argue that tokenization is more analogous to having a losslessly encoded image where you don’t have access to the decoder. Humans don’t perform well on that one.