Large Language Models
Overview
Students solve a technical problem to understand how simple neural networks work. Then, more broadly, they are prompted to think about vulnerabilities in large language model (LLM) chatbots.
Contributors
- Ethics content (Part 3 and Part 4) created by Uma Phatak, Veronica Rivera, Deveshi Buch, and Dan Jurafsky.
Ethics goals
- Understand the limitations of LLMs (e.g., hallucinations)
- Understand how LLMs can be used to cause harm (e.g., spread of mis/disinformation)