In this podcast episode, Sophie Bushwick and Tulika Bose discuss the dangers of artificial intelligence (AI) and large language models (LLM) in particular. You can listen to the recording twice. Read the questions carefully and choose the best alternative.
✲✲✲

7.1 What are the AI guardrails for? (3 p.)

Protecting the source code of the AI application
Keeping people from doing harm through the AI
Reducing errors in the answers provided by the AI


7.2 How have some people bypassed these guardrails? (3 p.)

By using flaws in the AI others found
By giving the AI false information
By asking the AI to break its rules