Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond
«Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond» è un corso online di RAG e AI engineering di livello avanzato, tenuto da InsightLearn Curated AI su InsightLearn. Il percorso comprende 8 lezioni organizzate in 2 sezioni, per una durata complessiva di 10h 0m. Go beyond basic prompting: CoT, ToT, self-consistency, constitutional AI, and systematic prompt optimization.
- Docente: InsightLearn Curated AI
- Categoria: RAG e AI engineering
- Livello: avanzato
- Durata: 10h 0m
- Accesso: gratuito in questa fase di validazione, in cambio di un feedback al termine
- Certificato: certificato di completamento verificabile online
Descrizione del corso
InsightLearn è in fase di sviluppo (work in progress): i contenuti di questa pagina sono pubblicati esclusivamente a fini di verifica e test.
A research-grounded course on advanced prompt engineering techniques. Covers chain-of-thought (CoT) and zero-shot CoT, tree-of-thoughts (ToT), self-consistency sampling, least-to-most prompting, generated knowledge prompting, automatic prompt optimization (APO), DSPy-style declarative prompting, constitutional AI and RLHF alignment prompting, adversarial prompt testing, and building systematic prompt evaluation pipelines.
Cosa imparerai
- Curated from public resources. Go beyond basic prompting: CoT, ToT, self-consistency, constitutional AI, and systematic prompt optimization.
Programma del corso
- Chain-of-Thought prompting: step-by-step reasoning (28 min)
- Zero-shot CoT: 'Let's think step by step' and variants (22 min)
- Tree-of-Thoughts: exploring multiple reasoning paths (32 min)
- Self-consistency: majority voting over multiple samples (20 min)
- Automatic Prompt Optimization (APO) with DSPy (40 min)
- Few-shot selection: semantic similarity vs random (25 min)
- Constitutional AI: value alignment via prompting (35 min)
- Adversarial prompt testing: red-teaming your own prompts (30 min)
Dalle lezioni
Estratto della trascrizione di «Chain-of-Thought prompting: step-by-step reasoning»
No more black box chat bot replies. Chain of Thought Prompting makes AI show its work. Chain of Thought Prompting, or COT, is a form of prompt engineering that emphasizes the step-by-step process of solving problems. Rather than inputting simple questions, this technique prompts a large language model to reveal its chain of thought or the rational steps taken to arrive at a final answer. In simple terms, COT. makes an LLM show its work. Here we'll discuss different types of COT prompting and how they work. For a detailed overview of different prompt engineering tools, click the link above or in the description below. The COT technique is not as simple as telling an LLM to show its work.…
Estratto della trascrizione di «Zero-shot CoT: 'Let's think step by step' and variants»
This right here was a short film made by me using AI tools. I will take you behind the scenes of this same project and show you how to use AI tools to not only come up with a story but actually bring it to life. So in this video I will show you step by step process to create AI powered films. So watch this video till the end without skipping any of the step. Welcome to AI upskill. Let me first explain you all. how we are going to create a movie, we will use ChatGPTT to create the story. Then this story will be used by an AI tool to create images. Then finally the generated images…
Estratto della trascrizione di «Tree-of-Thoughts: exploring multiple reasoning paths»
Imagine unlocking the full potential of AI, where it not only thinks but reasons like a human. This is the promise of the Tree of Thoughts, TOT, Method, a groundbreaking advancement in AI prompting. In this video, we'll explore the research paper, Tree of Thoughts, Deliberate Problem Solving with Large Language Models, published in December 2023. Developed by researchers from Google DeepMind and Princeton University, Tree of Thoughts, TOT, propels AI reason. to new heights, surpassing the widely used chain of thoughts, COT, method. Before we dive into the paper, let's first understand the background and why the need for Tree of Thoughts, TOT, emerged. Research on human problem solving reveals that we navigate complex problems by exploring a decision…
Altri corsi di RAG e AI engineering
- RAG from Scratch: Complete Retrieval-Augmented Generation
- Vector Databases in Production: Chroma, FAISS, pgvector
- Agentic AI Patterns: ReAct, Plan-and-Execute, and Multi-Agent
- AI Engineering: Building Production LLM Applications
- AI Safety: Alignment, Red-Teaming, Responsible Deployment
- Fine-Tuning LLMs: LoRA, QLoRA, and Full Fine-Tuning
Domande frequenti
Quanto dura il corso Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond?
Il corso dura 10h 0m in totale, con 8 lezioni suddivise in 2 sezioni, da seguire online al proprio ritmo.
Serve esperienza pregressa?
Il corso è di livello avanzato e non indica requisiti specifici di ingresso.
Il corso rilascia un certificato?
Sì: al completamento del corso ricevi un certificato di completamento verificabile online.