Natural Language Is an Unnatural Interface - by Varun
There is nothing, I repeat nothing, more intimidating than an empty text box staring you in the face. Especially if we don’t know who (or what) is on the other end. Yet here we are: You can ask a question, describe a situation for a haiku, or fantasize a new episode of Seinfeld, and it will provide a coherent answer. As you peer into the infinite possibilities opened up by that mere text box, it can be a struggle to string together the correct words. Much like how Googling is an art, so is ChatGPT-ing. In fact, ChatGPT-ing has it’s own name that has gained steam in the last few months: prompt engineering. The magic of ChatGPT is fundamentally its own constraint. As impressive as large language models (LLMs) are, they can be hard to prompt or control in the way that you want. Consider that the input to any LLM is natural language. Just talk to it like how you would talk to a human. Simple right? Not quite. Text input has infinite degrees of freedom. Literally anything and everything can
There is nothing, I repeat nothing, more intimidating than an empty text box staring you in the face. Especially if we don’t know who (or what) is on the other end. Yet here we are: “What do you ask? What can you ask? Anything? Like Google? What does that mean?” You can ask a question, describe a situation for a haiku, or fantasize a new episode of Seinfeld, and it will provide a coherent answer. As you peer into the infinite possibilities opened up by that mere text box, it can be a struggle to string together the correct words. Much like how Googling is an art, so is ChatGPT-ing. In…
saved by
related reading
- Why Chatbots Are Not the Future of Interfaceswattenberger.com
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- Prompt Engineering Guide | Prompt Engineering Guidepromptingguide.ai
- Doomprompting Is the New Doomscrolling.workingtheorys.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- How To Train Your Pet LLM: Prompt Engineeringtxt.cohere.com
- Natural language is the lazy user interface - Austin Z. Henleyaustinhenley.com
- Productizing Large Language Modelsblog.replit.com
- ChatGPT Is Dumber Than You Think - The Atlantictheatlantic.com
- Imagining better interfaces to language models | thesephist.comthesephist.com
- The Foundation Understanding LLMs and Prompt Engineering, and Why It All Mattersleeboonstra.dev
- Prompt Engineering Tips and Tricks with GPT-3 · andrew makes thingsblog.andrewcantino.com