I hereby solicit suggestions for the video of the day. Please email me your ideas with explanations. Selected entries will win 5 homework points. If your video is played at the beginning of class, you must also briefly explain something about the video and something about yourself - in person.
https://pollev.com/slade You may also download the app to your phone. Use the "slade" poll id.
Note: I tried both ChatGPT (through Yale's Clarity) and Google's learning portal (https://learning.google.com/experiments/learn-about.
The Google chatbot was stumped as well by Collatz. See Ed Discussion post.
We learn C because understanding how the computer manages memory is a fundamental part of CS. In C you can't avoid understanding if things are allocated on the heap or the stack, if you pass things by pointer or by reference. Yes there are languages that let you avoid that, but it's important to have a fundamental understanding of what the language you're using is hiding so you know how to use it well.
Similarly understanding how data structures work by building them by hand is important so that you understand the fundamentals of the performance tradeoffs between them.
In racket you're learning the fundamentals of recursion, and recursive data structures. Everything in racket is functions, and data structures that are defined in terms of themselves, e.g., linked lists, and trees. Recursively defined data structures and recursion more generally are fundamental to computer science.
Note: the collaboration quiz is separate. It coincides with the first homework assignment.
Title: AI Agents beyond ChatGPTAbstract:
ChatGPT has significantly raised public expectations for conversational agents,with many now anticipating these agents to handle a wide range of tasks. However, deploying one single larger model with generalized capabilities with simple prompting is often impractical to complete these tasks. There are various issues in terms of accuracy, cost, and security, particularly in industry settings. Solving tasks requires a systematic combination of different models to form AI agent orchestration. In this talk, we will explore various approaches to achieve that through diverse techniques including Reflection, Monte Carlo Tree Search, etc.
Bio:
Zhou (Jo) Yu is an Associate Professor at Columbia University’s Computer Science Department and Founder of ARKLEX.AI. She obtained her Ph.D. from Carnegie Mellon University. Dr. Yu has received several best paper awards in top NLP conferences and has won Forbes 30 under 30 in 2018. Dr. Yu has developed various AI systems that have had a real impact, including winning the Amazon Alexa Prize. Dr. Yu co-founded ARKLEX.AI, focusing on democratizing AI Agent building with GenAI developer tools.
website: https://www.cs.columbia.edu/~zhouyu/
Recursion.html (jupyter) deep recursion.