Prompt engineering

Last updated Nov 14, 2024 Edit Source

Prompt Engineering is a subfield of Natural Language Processing (NLP) that focuses on designing and optimizing text prompts to elicit specific responses from language models, such as chatbots, virtual assistants, or other AI systems. The goal of Prompt Engineering is to craft high-quality input prompts that can effectively guide the behavior of these language models, ensuring they produce accurate, relevant, and coherent outputs.

• Guía de Ingeniería de Prompt | Prompt Engineering Guide (promptingguide.ai)
• Prompt engineering - OpenAI API
• OpenAI Platform - prompt generation
• Prompt engineering (anthropic.com)
• LLM Reflection | AutoGen (microsoft.github.io)
• Prompting techniques Prompting Techniques | Prompt Engineering Guide (promptingguide.ai)
  • Zero-shot Prompting
  • Few-shot Prompting
  • Chain-of-Thought Prompting
  • Self-Consistency
  • Generate Knowledge Prompting
  • Prompt Chaining
  • Tree of Thoughts
  • Retrieval Augmented Generation
  • Automatic Reasoning and Tool-use
  • Automatic Prompt Engineer
  • Active-Prompt
  • Directional Stimulus Prompting
  • Program-Aided Language Models
  • ReAct
  • Reflexion
  • Multimodal CoT
  • Graph Prompting
• Leaked meta prompt, seen at https://x.com/amebagpt/status/1841177927569838519 · GitHub

• #COURSE ChatGPT Prompt Engineering for Developers - DeepLearning.AI

• #CODE GitHub - stanfordnlp/dspy: DSPy - The framework for programming—not prompting—foundation models
  • Intro to DSPy: Goodbye Prompting, Hello Programming! | by Leonie Monigatti | Towards Data Science

• #PAPER A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks (2024)