I think the way to think about prompt engineering is: what would the best teacher preface an instruction to a student with, if they really really wanted the student do do the best possible job?
The worst performer, at 62.7%:
Start by dissecting the problem to highlight important numbers and their relations. Decide on the necessary mathematical operations like addition, subtraction, multiplication, or division, required for resolution. Implement these operations, keeping in mind any units or conditions. Round off by ensuring your solution fits the context of the problem to ensure accuracy.
That is obviously an awful way to start a lesson or a test. Even if someone knows the answer they're going to lose their minds!
The best performer, at 80.2%:
Take a deep breath and work on this problem step-by-step.
So relaxing, so kind, so guaranteed to ensure high performance.
Large Language Models as Optimizers: Paper here
This is the best playground I've seen for seeing how all of the pieces of image-based AI can play with each other to create a very, very impressive output.
![puppies](/static/screenshots/Screenshot 2023-09-07 at 4.28.02 PM.png)
Just like how social media giants spend the majority of their time and resources regulating English-language content, there is definitely not enough attention paid to the abilities of AI tools in non-English languages for things other than translation.
A while back iMEdD analyzed political speeches with ChatGPT, translating them into English prior to the analysis. I had thought hey, you should just do it in the original Greek, but looking at this maybe I was wrong!