Prompt Engineering Insights
Nathan and Riley delve into the complexities of prompt engineering, questioning the effectiveness of human preferences in evaluating models, particularly with ASCII art. They discuss the evolving nature of model interactions, highlighting the need for new prompting instructions and the potential for models to become less sensitive to specific prompts over time. The conversation reveals a nuanced understanding of how model behavior may converge in the future, challenging conventional wisdom in the field.In this clip
From this podcast
Interconnects Audio
Interviewing Riley Goodside on the science of prompting
Related Questions