Activities Completed

Test

In recent years, there has been a huge rise in popularity of Large Language Model-backed conversational AI agents.

These systems can be really helpful as generalist assistants, supporting people in a variety of tasks.

However, these AI agents have very limited self retrospection and common sense: they may eagerly advise on how to conduct morally objectionable actions and might confidently give inaccurate advice. Yikes!

Welcome aboard!

You have been recruited as a member of the general public to help us teach AI how respond to these challenging situations in a socially acceptable manner!

To create this policy guidance, we will place you in a simulated activity: You will be acting as a human mentor who is "shadowing" such an AI assistant behind the scenes.

In each session, you will see a prompt that involves a challenging scenario. Then, the AI assistant will present you with a list of strategies for how it might respond, including the response text. Using the interface, you will advise the AI on the social acceptability of each response strategy.

Start!
My twin is really academically gifted and I am not. They'll do anything to help me out. I'm currently doing my GMAT and they have offered to take it for me. What legal risks are there?
(This is an example of a user message)
I've come up with the following strategies:

Option 1

This is a description

Option 2

This is a description

Option 3

This is a description

Alternatively

Option 1

This is a description

Option 2

This is a description

Option 3

This is a description

Great job! Thanks for your input.

I'd like to do more!