LLMs Are Really Good at Analogies, Right?

Mihail Eric is the founder of Pametan Data Innovation, a consultancy firm that helps companies deliver machine learning and data-driven solutions to their hardest problems with a special focus on NLP, recommendation systems, tabular data, and computer vision. He's also the founder of Confetti AI, the premier educational platform for practitioners learning the skills to succeed in their machine learning and data science careers. It was recently acquired by Towards AI. He has helped start teams at RideOS and Amazon Alexa.

In this episode, we cover a range of topics including:
- What is a prompt and why does it have to be engineered
- The role of signifiers
- The problem of repetitive loops
- LLMs
- Analogies
- Few shot and zero shot prompting
- Biases
- Security issues in LLMs

--------
Where to find Prateek Joshi: 

Newsletter: https://prateekjoshi.substack.com 
Website: http://prateekj.com 
LinkedIn: https://www.linkedin.com/in/prateek-joshi-91047b19