Directory
Published directory entries matching your search.
Prompt Engineering Lil'Log is a blog post focused on prompt engineering for autoregressive language models. It covers methods to steer large language model behavior without updating model weights, including zero-shot prompting, few-shot prompting, and chain-of-thought prompting.
A blog post summarizing a University of Illinois study on solo performance prompting (SPP), a prompt engineering method in which an LLM summons multiple personas that collaborate on a task. The post describes the SPP prompt structure and reports on three experiments: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle.
A guide to prompt engineering that collects papers, advanced prompting techniques, learning guides, model-specific guides, lectures, references, new LLM capabilities, and tools related to prompt engineering. It describes prompt engineering as a discipline for developing and optimizing prompts to use language models across applications and research topics, and offers courses on prompting and building AI agents.
The Art of ChatGPT Prompting: A Guide to Crafting Clear and Effective Prompts creates or edits images with generative AI and text-based controls.
This Notion page is titled 'Tricks for prompting Sweep' and is associated with Notion's collaborative AI workspace. The workspace is built to let users build and orchestrate AI agents alongside their team's existing projects, meetings, and connected applications.
Google AI Studio is a browser-based workspace for experimenting with Gemini and building apps from prompts. The saved link opens its apps area and requires Google sign-in.
A GitHub Education program offering the best developer tools free for students, created with partners because real world tools can be cost-prohibitive for most students. It also includes curated Experiences bundles with tutorials and resources for learning skills such as GitHub Flow, open source contribution and AI prompting.
Anthropic's educational courses repository contains five courses covering the Claude SDK, prompt engineering, real world prompting, prompt evaluations and tool use. Suggested order begins with Anthropic API fundamentals. The repository was archived by its owner and is read-only. Courses often favor the lowest-cost model, Claude 3 Haiku, to keep API costs down.
Anthropic Prompt Engineering documentation on the Claude Platform provides an overview of prompt engineering. It explains when prompt engineering is appropriate, presents Claude prompting techniques, and includes interactive tutorials for developers.
Bolt.new is an AI-powered web development agent for prompting, running, editing, and deploying full-stack applications from the browser without local setup. It uses StackBlitz WebContainers to run npm tools, Node.js servers, and third-party APIs, giving AI models control over the filesystem, terminal, and package manager.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Direct is a chat tool for interacting with multiple frontier AI models. It allows prompting several open source and proprietary large language models in one place, for research, coding, and creative tasks.
LearnPrompting is a free educational resource focused on generative AI and prompt engineering. It provides a comprehensive guide suitable for both beginners and advanced users, with structured courses, modular learning content, specialized topics including prompt hacking and image prompting, and supplementary resources such as a vocabulary guide and community support.
DSPy is a framework developed by Stanford NLP for programming language models rather than using traditional prompting workflows. The open-source project is hosted on GitHub, with official documentation available at dspy.ai.
TavernAI is an AI roleplay chat platform with an advanced prompting system. It supports running machine learning models locally or connecting to external AI providers, and can be adapted to function as an AI game engine.
Voyager is an LLM-powered embodied agent for Minecraft that explores, acquires skills, and makes discoveries without human intervention. It combines an automatic curriculum, a skill library of executable code, and an iterative prompting mechanism using environment feedback, execution errors, and self-verification. It interacts with GPT-4 through blackbox queries, avoiding model parameter fine-tuning.
