Sander Schulhoff | NLP Researcher, LearnPrompting.com Founder & CS Student (original) (raw)

Hi, I'm Sander Schulhoff. I am the CEO of LearnPrompting.org, the first guide on Prompt Engineering.

I also do research in Deep RL and NLP, most recently publishing massive scale studies in the fields of prompting and prompt security. I have worked variously on the boardgame Diplomacy, Deep RL in Minecraft, Event Camera Video Classification, Plant Identification, Wetland Mitigation Banking, and Prompt Engineering/Hacking. I also advise Inventory Quant.

ENMLP2023 Best Theme Paper Presentation

Learn Prompting

December 2022 -

Co-Founder and CEO

Website

Learn Prompting is a comprehensive guide to understanding and mastering the art of prompt engineering. It covers various techniques and strategies to effectively communicate with AI models, helping you get the most out of AI-powered tools and applications. Whether you're a beginner or an experienced user, this resource will enhance your skills in crafting prompts for optimal results.

HackAPrompt

Spring 2023

ReactNode

Organized the first and largest competition on prompt injection. Secured $40K in sponsorship from major companies, including OpenAI, HuggingFace, and Scale. Collected and published the largest dataset of prompt injections (600K+ adversarial prompts) and developed the first taxonomical ontology of Prompt Hacking. The paper won Best Theme Paper at EMNLP2023.

Paper

HackAPrompt

The Prompt Report

Spring 2023

LLMs

Ran the largest study on prompting ever done. I lead a team of 32 researchers from U Maryland, OpenAI, Microsoft, Princeton, Stanford, and other institutions. Surveyed over 1500 papers and created a systematic literature review with comprehensive taxonomies of 100s of techniques.

Paper

The Prompt Report