AI Dynamics

Global AI News Aggregator

About

Placeholder Syntax Reliability and Tokenization Issues in GPT Models

I haven’t tried it but agree {placeholder} syntax is pretty reliable in practice for GPT-3.5 and up; more generally you do see issues I suspect are tokenization related. E.g. 4 can struggle to notice ““python” (for a Markdown code block) is missing a backtick.

→ View original post on X — @goodside