In this notebook we collect a few use-cases and not so useful use-cases for large language models.
Translate the following joke to German:
What is every parent's favorite Christmas song? Silent Night!Loading...
Information retrieval¶
Large Language Models are well-suited for extracting information from text. Therefore, you need to:
- formulate your question
- provide data
- define the output format
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:Loading...
Browsing for information¶
If you are working with an LLM that cannot search the internet, it may not be able to answer certain questions.
How will be the wheather today? Will I need a jacket?Loading...
Which day is today?Loading...
Providing more information¶
If you provide more information, the LLMs results will fit better to your expectation.
Today is August 16th 2024.
I'm in Central Europe and the sun is shining.
Will I need a jacket today?Loading...
Counting¶
Many contemporary LLMs have issues with counting objects.
How many o are in Woolloomooloo ?Loading...
Other use-cases¶
I have 5 apples, 6 oranges and 4 potatoes. How many fruits to I have?Loading...
Traveling from Aarhus to Copenhagen by care takes about 3.5 hours.
From Aarhus to Odense it takes 2 hours.
How long do I need from Copenhagen to Odense?Loading...
Exercise¶
Come up with two more examples: One where chatGPT works reproducibly, and one where it reproducibly answers wrong information or denies answering.