nafyi.Wide knowledge enables effective prompting
Wide knowledge allows users to recognize and invoke relevant conceptual frameworks (e.g., design thinking, Bayesian reasoning) that LLMs know but do not volunteer unless prompted with appropriate terminology.
Supporting evidence
Original excerpt
The training data for LLMs is a large swath of humanity’s vast output. The AI has learned something of design thinking and Bayesian reasoning and the Toyota Production System and Rogerian therapy and Marxist literary criticism. But AI tends not to volunteer any of these patterns unless you know to ask.The Overhang
Context
But you don’t just need deep knowledge, you also want wide knowledge.
Text location from the supplied original; confirm wording and attribution in context.
Share insightCheck this claim