Mitigating model limitations

Understanding Prompt Engineering

Alex Banks

Founder & Educator

Introduction to model limitations

 

Group 84.png

Understanding Prompt Engineering

The reversal curse

 

Group 85.png

Understanding Prompt Engineering

The reversal curse

Group 86.png

Understanding Prompt Engineering

Biases - a mirror of Society

 

Group 87.png

Understanding Prompt Engineering

Hallucinations - when the model imagines

 

Group 88.png

Understanding Prompt Engineering

Hallucinations - when the model imagines

 

Group 89.png

Understanding Prompt Engineering

Hallucinations - when the model imagines

 

Group 90.png

Understanding Prompt Engineering

Overfitting - echoing the data

Model is too closely tailored to its training data.

Makes it less effective at generalizing to new, unseen data.

image_115__3_-removebg-preview 1.png

Understanding Prompt Engineering

Overfitting - echoing the data

Comedy challenges large language models like ChatGPT.

Researchers found that 90% of 1,008 generations were the same 25 jokes.

image_115__2_-removebg-preview 1.png

Understanding Prompt Engineering

Overfitting - echoing the data

Group 91.png

Understanding Prompt Engineering

Let's practice!

Understanding Prompt Engineering

Preparing Video For Download...