Build your own chatbot: Thinking about Language through ChatGPT
This Pod will meet once per week for 6 weeks, starting on August 22, 2023 at 8:00pm EDT/5:00pm PDT, with the last session being Tuesday September 26, 2023.
By enrolling you confirm this time works for you.
Date and time
Tuesday, 8:00pm EDT/5:00pm PDT
Group size
1-6 students
Outcome
A customized ChatGPT language-based application
Tuition
$495
TAUGHT BY
Ross
PhD candidate in Computer Science
This pod has already started.
Check out other Pods and find which fits you best!
Browse available Pods
Build your own chatbot: Thinking about Language through ChatGPT
Gone are the days where we can identify a human by simply asking them to click the “I am a human” checkbox. Large language models have even enabled computers to talk like humans (and not just single sentences – long, continuous conversations!). With these new models, we enter an era where programs can assist humans with more personalized, instructive, helpful language than ever before. How do these models work, and how can we leverage technology like ChatGPT to directly improve our lives?
ABOUT THE MENTOR
Ross
PhD candidate in Computer Science
Ross Greer - I use computer vision & artificial intelligence to create human-aware systems for applications in intelligent vehicles, virtual classrooms, and even concert halls! At school, you'll find me spending my time in two labs: the Laboratory for Safe & Intelligent Vehicles (PI Mohan Trivedi) & the Center for Research in Entertainment & Learning (PI Shlomo Dubnov). Some problems I solve with my research are prediction of vehicle trajectories in real-world driving scenarios, estimation of driver state & readiness behind the wheel, and understanding & communicating human gaze & gesture during live musical performances. My work even teaches computers how to compose music using artificial intelligence, working towards human-AI "co-creativity"! I love to create music, and I feel lucky to combine two of my passions in part of my research & teaching. Outside of my academic work, I advise the Symphonic Student Association at UCSD, and field direct & write music for the Marching Band at UC Berkeley. One of my favorite hobbies is traveling to conduct workshops around the world!
Build your own chatbot: Thinking about Language through ChatGPT
Week by week curriculum
Week 1
Beginnings of AI: The Turing Test In this session, you will learn who Alan Turing was, and describe his Turing Test. You will relate this Turing Test to its modern derivatives (CAPTCHAs, BONGO), and discuss whether ChatGPT passes the Turing Test.
Week 2
How do programmers use ChatGPT? You will learn what an API is, and learn about how companies, researchers, and engineers which maintain APIs and repositories for public use (plus, you will learn how to cite and acknowledge their contributions in your projects). By the end of this session, you will make your own call to the ChatGPT API in Python.
Week 3
Tokenization and Encoding You will learn some ways we can break apart a word or sentence into tokens. You will learn one way that AI researchers “encode” these tokens into numeric objects, and discuss challenges associated with so-called “sparse” encoding schemes.
Week 4
Embedding You will learn what “word embedding” means, and how it allows for a more meaningful and compact representation of words. You will write programs to illustrate the “distances” between words.
Week 5
How does ChatGPT work? You will learn the basic settings of Reinforcement Learning, and specifically learn about the environment, actions, and rewards associated with ChatGPT’s training framework. You will also learn how human input is integrated into the ChatGPT learning pipeline.
Week 6
Build a ChatGPT app! In this session, you will build an interactive ChatGPT app in Python, designing your app to address a problem of your choosing.