Prompt Engineering Guide
๐Ÿ˜ƒ Basics
๐Ÿ’ผ Applications
๐Ÿง™โ€โ™‚๏ธ Intermediate
๐Ÿค– ะะณะตะฝั‚ั‹
โš–๏ธ Reliability
๐Ÿ–ผ๏ธ Image Prompting
๐Ÿ”“ Prompt Hacking
๐Ÿ”จ Tooling
๐Ÿ’ช Prompt Tuning
๐ŸŽฒ Miscellaneous
Models
๐Ÿ“™ Vocabulary Reference
๐Ÿ“š Bibliography
๐Ÿ“ฆ Prompted Products
๐Ÿ›ธ Additional Resources
๐Ÿ”ฅ Hot Topics
โœจ Credits
๐Ÿ”จ ToolingPrompt Engineering IDEsHuman Loop

Human Loop

Reading Time: 1 minute
Last updated on August 7, 2024

Sander Schulhoff

Human loop appears to offer a playground similar to the GPT-3 Playground, but with some added features. They are currently working with more industry users.

Features

  1. Provides a simple SDK to log the GPT-3 requests and user feedback.
  2. Provides feedback on the user inputs and discovers issues user is missing.
  3. Users will be able to log explicit and implicit signals through SDK.
  4. Users will be easily A/B test models and prompts with the improvement engine built for GPT-3.
  5. Users will be able to Compare prompts on different models and find the best model and reduce cost.

Sander Schulhoff

Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.