Prompt Engineering

97 bookmarks
Custom sorting
Aligning language models to follow instructions
Aligning language models to follow instructions
We’ve trained language models that are much better at following user intentions than GPT-3 while also making them more truthful and less toxic, using techniques developed through our alignment research. These InstructGPT models, which are trained with humans in the loop, are now deployed as the default language models on our API.
·openai.com·
Aligning language models to follow instructions
The ONE ChatGPT Prompt to Rule Them All 👑
The ONE ChatGPT Prompt to Rule Them All 👑
This could be one of THE best ChatGPT prompts you have ever seen. Prompt engineering just became a whole lot easier 😉👉 Here is the prompt for you guys: htt...
·youtube.com·
The ONE ChatGPT Prompt to Rule Them All 👑
ChatGPT Gets Its “Wolfram Superpowers”!
ChatGPT Gets Its “Wolfram Superpowers”!
Wolfram plugin gives computationally accurate answers to ChatGPT queries using Wolfram's data knowledgebase and language. Custom visualizations are given as well. Stephen Wolfram explains how it works.
·writings.stephenwolfram.com·
ChatGPT Gets Its “Wolfram Superpowers”!
Can ChatGPT copy your writing style?
Can ChatGPT copy your writing style?
People who write about GPT point note how its default output has a pretty plain style. In fact, I’d probably say its style approaches the…
·markcmarino.medium.com·
Can ChatGPT copy your writing style?