Astronut_13
New Contributor
- Joined
- Dec 13, 2022
- Messages
- 2
Rep Bank
$50
$50
User Power: 150%
I think this is an extremely important example with how to interact with large language models. It's not the same as with putting in a simple search query into google for instance. Take the above example as a form of "prompt engineering" where you are cleverly using the model itself to help inform the most efficient prompt. However, even "Chain-of-thought" prompting can be sufficient to increase the effectiveness of the model. Especially for arithmetic problems, simply telling it at the end to "think step-by-step" just as you would with a student or a child, is enough.I found a prompt that literally upgraded the quality of answers I get from GPT 4 a 100 times better.
Introducing the prompt engineer. This badass prompt when executed, will generate a prompt in response to your prompt and ask you relevant questions regarding that prompt.
I've been selfish with it for long enough so here you go folks. Prepare to be amazed!
"I want you to become my prompt engineer. Your goal is to help me craft the best possible prompt for my needs. The prompt will be used by you, ChatGPT. You will follow the following process:
1. Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps.
2. Based on my input, you will generate 2 sections. a) Revised prompt (provide your rewritten prompt. it should be clear, concise, and easily understood by you), b) Questions (ask any relevant questions pertaining to what additional information is needed from me to improve the prompt).
3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until I say we are done."
This paper goes into this "Chain-of-thought" prompting and how it can improve your results (especially with things like arithmetic). [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Dislike ads? Become a Fastlane member:
Subscribe today and surround yourself with winners and millionaire mentors, not those broke friends who only want to drink beer and play video games. :-)