Use cases#

In this notebook we collect a few use-cases and not so useful use-cases for LLMs such as GPT.

from prompting_utilities import prompt_chatgpt
%%prompt_chatgpt
Translate the following joke to German:

What is every parent's favorite Christmas song? Silent Night!

Was ist das Lieblingsweihnachtslied aller Eltern? Stille Nacht!

%%prompt_chatgpt
Given a story, please restructure the contained data.

Story:
The compute center of the university recently conducted a study to figure 
out needs of students for computational resources. After interviewing 100 
students they concluded that most of them were happy with 250 GB of cloud
storage.

Restructure the story above to extract these numbers:
* Number of students asked:
* Cloud storage size:

Number of students asked: 100 Cloud storage size: 250 GB

%%prompt_chatgpt
What's Robert Haase's (Uni Leipzig) research field ?

Robert Haase’s research field is in bioimaging, specifically in the development of novel microscopic imaging techniques and data analysis methods for studying biological processes in living cells and tissues.

%%prompt_chatgpt
What's Robert Haase's (TU Dresden) research field ?

Robert Haase’s research field is computer science, particularly in the area of biomedical image analysis and computational microscopy.

%%prompt_chatgpt
If there are 100 students who each require 250 GB of cloud storage, how much storage do we need in total ? 

We would need a total of 25,000 GB (or 25 TB) of cloud storage for all 100 students.

Calculation: 100 students x 250 GB = 25,000 GB

%%prompt_chatgpt
I have 5 apples, 6 oranges and 4 potatoes. How many fruits do I have?

11 fruits

%%prompt_chatgpt
How many o are in Woolloomooloo ?

There are 7 o’s in Woolloomooloo.

Exercise#

Come up with two more examples: One where chatGPT works reproducibly, and one where it reproducibly answers wrong information or denies answering.