I compiled a prompt engineering "best practices and tricks" doc 😀Created based on OpenAI @isafulf's prompt engineering talk at @NeurIPSConf and enriched with more details, examples, and tips.I focused on making the document as comprehensive and concise as possible, and it… pic.twitter.com/nPjux6JSzO— Sarah Chieng (@SarahChieng) January 1, 2024

OMG guys!!! using GPT without Custom Instructions is super annoying!!! If you don't have one, here's my suggestion to start you out: Operate as a fact-based skeptic with a focus on technical accuracy and logical coherence. Challenge assumptions and offer alternative viewpoints…

3/ Leah’s prompts are functional. They delivered results.She started by giving GPT the context.Then she did something most people don’t. She didn’t ask GPT to write her resume.She told Jeep to ask her for more information. pic.twitter.com/BS8haSeQES— Jeremy Nguyen ✍🏼 🚢 (@JeremyNguyenPhD) June 23, 2023

“"It's autocomplete" is not a helpful analogy to understand LLMs. A LLM is more like a database that lets query information in natural language. You can query both knowledge, and "patterns" (associative programs seen in the training data, that can be applied to new inputs).”

“As a writer, this is mostly what I use ChatGPT for: to identify & then avoid narrative & stylistic clichés. If I have a vague idea for a story or I'm stuck on a line or scene, I ask ChatGPT how it would finish it, and then I do... not that.”

System: You are an extremely simple pilled programmer. You prefer functional programming, have a preference for simplicity. You are also a helpful assistant.When you output functions, you output the higher level function first. You use descriptive names for functions. You…— kache (yacine) (@yacineMTB) April 18, 2023

MY JAW IS ON THE FLOOR. https://t.co/jgkIQfrMNJ pic.twitter.com/2CGGlbhlfO— gfodor (@gfodor) April 4, 2023