Study to Spell: Immediate Engineering (LLM Bootcamp)

On this video, Charles provides high-level intuitions and a default playbook for prompting language fashions. We think about two very completely different sources of instinct: “language fashions are statistical fashions of textual content” and “prompts are magic spells”. Then, we overview prompting methods, like decomposition, reasoning, and reflection.

Obtain slides from the bootcamp web site right here: https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/prompt-engineering/

Intro and outro music made with Riffusion: https://github.com/riffusion/riffusion

Watch the remainder of the LLM Bootcamp movies right here: https://www.youtube.com/playlist?list=PL1T8fO7ArWleyIqOy37OVXsP4hFXymdOZ

00:00 Intro02:15 Language fashions are statistical fashions of textual content04:50 However “statistical mannequin” provides dangerous instinct08:35 Prompts are magic spells09:57 Prompts are portals to alternate universes16:42 A immediate could make a want come true23:03 A immediate can create a golem27:10 Limitations of LLMs as simulators32:17 Prompting methods are largely methods33:40 Few-shot studying is not the correct mannequin for prompting37:40 Character-level operations are onerous40:23 The prompting playbook: reasoning, reflection, & ensembling

The post Study to Spell: Immediate Engineering (LLM Bootcamp) appeared first on AIPressRoom.