10 Exciting Project Ideas Using Extended Language Models (LLM) for Your Portfolio | by Léonie Monigatti

Learn how to build apps and showcase your skills with Large Language Models (LLM). Get started today!

A data science portfolio is a way to create public evidence of your skills.

OhA common piece of advice I hear a lot for job candidates is to have a portfolio showcasing your work. This doesn’t just apply to artists or models, but also to software developers and data scientists.

A portfolio of your projects provides public proof of your skills. This public evidence can range from a blog to open source contributions to active engagement on forums such as StackOverflow. But this type of public evidence takes a long time to build.

Another type of proof showcasing your skills is small, end-to-end projects.

Another type of proof showcasing your skills is small, end-to-end projects. For data scientists, these could be projects such as exploratory data analysis and data visualization, classic machine learning on tabular data, or deep learning to classify images.

With the advent of large language models (LLMs) in the form of pre-trained base models, such as OpenAI’s GPT-3, the opportunities to create interesting things with LLMs are endless. And with the emergence of development toolsthe technical barrier decreases.

So now is the perfect time to add a new LLM-powered project to your portfolio!

This article will share 10 side project ideas that use LLMs for downstream tasks. Wherever you are in your career, I hope this inspires you to build something fun while learning about this new technology.

  1. Cover letter generator
  2. Chatbot with a personality
  3. YouTube Summary
  4. Extracting information from job offers
  5. Custom Web Scraper
  6. Searchable database of your documents
  7. Answering questions about documents
  8. Group social media posts and podcast episodes into topics
  9. Classify sales inquiries from emails

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *