When LLM gained attention, everybody thought they should master the art of writing good prompts and hence Prompt Engineering became a thing. LLM’s are however just a Deep Learning (DL) model that can be treated like any other DL model. When realising this, we should divert from the somewhat alchemistic path of Prompt Engineering (optimisation theory) and instead focus on declarative methods (optimisation algorithms).
In this presentation we will dive into how Prompt Engineering has evolved and why we can benefit from an assumption-less DL model by compiling declarative language model calls into self-improving pipelines.
Dette er fra konferencen "Driving AI 2024".
AI-teknologi med overvægt til den nørdede side – åbent for alle med en nysgerrighed for AI's fremtid.
Thumbnailen er AI-generet.