If you’re looking to learn more about prompt engineering, here’s a good survey paper that outlines the different types of prompt engineering (link provided in alt) Here are some of the strategies discussed:
•Chain of Thought (CoT)
•Chain of Cause (CoC)
•Program-Aided Language
PROMPT ENGINEERING
-
Survey on Prompt Engineering Strategies and Techniques
By
–
-
Fine control and 5-10 second prompts
By
–
I think there’s a tipping point with fine control where you’d only want to make 5-10 seconds at a time due to the amount of detail you’ll demand from the prompt. Longer is possible, but it might now be necessary. You want to achieve a specific result and be able to steer it
-
Building Autonomous AI Agents for Complex Multistep Workflows
By
–
The next frontier in generative AI is here: Agentic AI. In our latest post, we walk you through how to build autonomous AI agents that go beyond reactive tasks to execute complex, multistep workflows independently. Dive into the 7 critical resources and skills needed to
-
ChatGPT Prompts to Start Your Online Business
By
–
Want to build a business online? Use these ChatGPT business prompts to get started: https://
godofprompt.ai/blog/chatgpt-p
rompts-for-small-businesses
… -
GPT helps write emails in various tones and styles
By
–
9. Email writer I hate email writing. Its not like I don't know how to write them but it's a lot of work. This GPT can help you out by writing emails in a lot of tones and styles. Link: https://
chatgpt.com/g/g-SLkL4uUYY-
email
… -
Mega-prompt generator for ChatGPT
By
–
1. Mega Prompt Generator
— God of Prompt (@godofprompt) 16 août 2024
To get exact and precise content from ChatGPT, give mega prompts to it.
This GPT can help you out.
Link: https://t.co/DdvLxY0DCg pic.twitter.com/q8iwOWW2AX—
1. Mega Prompt Generator To get exact and precise content from ChatGPT, give mega prompts to it. This GPT can help you out. Link:
https://chatgpt.com/g/g-1ObGhQpzP-mega-prompt-generator
…
— -
Many-shot examples and their effect on in-context learning
By
–
I’m not convinced many-shot examples degrade performance. Artificial distractor text will, as will long inputs, but many (diverse, reasonable) examples in traditional k-shot ICL should strictly help performance at the (now much lower) expense of latency/cost.
-
Grok Fun Mode Image Generation Olympic Athlete Pole Vault
By
–
Did I get this result on Grok because I was using the Fun Mode? "Create an image of an olympic athlete crossing pole vaulting over the Eifel tower."
-
Why “fine-tuning” is a misleading term for LLM updates
By
–
“Fine-tuning” is an unfortunate term. FT makes “fine” updates to model weights, but these can effect radical changes in almost any aspect of LLM behavior — to a user it’s more like “retraining.” This makes any use of FT’s lay definition (“tweaking”) in AI contexts confusing.
-
Improve LLM Application Accuracy with New Short Course
By
–
Learn a development pattern to systematically improve the accuracy and reliability of LLM applications in our new short course, Improving Accuracy of LLM Applications, built in partnership with @LaminiAI and @Meta, and taught by Lamini’s CEO @realSharonZhou, and Meta’s Senior… pic.twitter.com/b3YogwxPle
— Andrew Ng (@AndrewYNg) 14 août 2024Learn a development pattern to systematically improve the accuracy and reliability of LLM applications in our new short course, Improving Accuracy of LLM Applications, built in partnership with @LaminiAI and @Meta
, and taught by Lamini’s CEO @realSharonZhou
, and Meta’s Senior