I’ve been working extensively with ChatGPT-4 and ChatGPT-4o over the past few months, developing complex prompts to analyse contracts and automate the drafting of mitigations and controls for identified risks. To support those beginning their journey with prompt engineering, I’ve decided to start sharing some of the resources I have found to be helpful. Today’s resource might seem a bit daunting at first, but it’s incredibly instructive if you take the time to work through it. Check out this guide on prompt engineering by OpenAI: https://lnkd.in/gi_AJFJk
Clive Hutcheon’s Post
More Relevant Posts
-
Postdoctoral Researcher at Modul University Vienna and Modul Technology ■ Large Language Models ■ Knowledge Graphs ■ NLP ■ Data Science ■ Information Visualization
Here is an introductory Prompt Engineering Guide from the makers of ChatGPT https://t.co/xhNBs9niQx
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
OpenAI recently released a prompt engineering guide with 6 specific strategies to help you unlock ChatGPT’s potential
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
Thoughtful Leadership and Insights | Building a Better Tomorrow | Growing Bright Ideas in Brilliant People
Checkout the 'real' prompt engineering guide, per OpenAI! This is quite different than other material - this is a descriptive guideline of how ChatGPT is supposed to work. It's like the manual that comes with your car. Before this, prompt engineering guides were more of a game of inference based on people playing with a black box. https://lnkd.in/gzdVTeha
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
The concepts used in RAG are the same you should use to do prompt engineering and make better ChatGPT evals. When you add context to your prompts, you are doing the retrieval manually instead of automatically querying a vector database for documents. This concept can greatly enhance your usage of ChatGPT and save you a lot of time. This is the 2nd of 5 follow-ups to a previous post on RAG + Vision tasks. https://lnkd.in/ggJjaDEk In this OpenAI guide on Prompt Engineering (https://lnkd.in/g49ppNw6), the 2nd strategy (of 6) is to "Provide reference text". You are doing the manual work to provide a meaningful context; we can think of this as "fine-tuning your model" with new data. Here is an example. USER <insert articles, each delimited by triple quotes> Question: <insert question here>
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
Link to official article : https://t.co/xhNBs9niQx Find below the final roadmap to Prompt Engineering with Chatgpt. #dataengineer #datascientist #dataanalyst
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
OpenAI just released a prompt engineering guide to improve your results with ChatGPT. Worth a read! https://lnkd.in/gWWS9nAA #generatieveai #artificialntelligence #chatgptprompts
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
https://lnkd.in/gVdnkinw prompt engineering guide out of OpenAI, a good read no matter where you are with your knowledge of ChatGPT or LLMs more generally
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
<rant> So far, those chaps selling 10,000 or 20,000 ChatGPT prompts have 99.9% terrible prompts! Someone showed me an example of them: "How do I create a scalable business?" "Write me an article about (content) in 1500 words." Really?!?!? (kill me already) Just proof that quantity is not enough as a value proposition. Check out the absolutely free OpenAi ChatGPT prompt page for better prompt engineering, stop paying for this crap load of... crap lol. </rant> https://lnkd.in/ggbQVsTr
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
OpenAI have just released a really good and comprehensive guide on prompt engineering: https://lnkd.in/eKt64KUi. While I think guides like this are a useful way to improve your prompting once you're already familiar with tools such as ChatGPT, I wouldn't recommend it for anyone just starting out. My main advice for anyone new is just to play around and figure what works and doesn't for you (i.e., f**k around and find out).
OpenAI Platform
platform.openai.com
To view or add a comment, sign in
-
A must read article for anyone who is using ChatGPT and want to get better results. It covers 6 strategies for getting better results Write clear instructions in summary: 1. Write clear instructions 2. Provide reference text 3. Split complex tasks into simpler subtasks 4. Give the model time to think 5. Use external tools 6. Test changes systematically Happy prompting everyone 🤖
OpenAI Platform
platform.openai.com
To view or add a comment, sign in