Student project for engaging with AI alignment

Anyone can undertake this project, and feel free to make use of the complete project description with all details needed to undertake this project individually or as a facilitator. Message plex#1874 on Discord after adding him as a friend for invites to Robert Miles’ AI Discord, and to receive an onboarding call if you want to run a similar project.

Short description

Robert Miles is a successful YouTuber making AI Safety related content. Robert Miles’ AI Discord community is working on an interactive FAQ as a single point of entry into alignment (WIP prototype), and the wiki which stores questions and answers is ready to be used. Participants would write and organize questions and answers on Stampy’s Wiki, and give feedback on the software. This project is fit for students looking for ways to contribute to AI alignment and getting involved while learning.

Evaluation

The first iteration of this project has recently been tested by 4 members of EA NTNU, all of them being students, working 3 hours weekly for 6 weeks. EA NTNU is an engagement driven local group at the Norwegian University of Science and Technology (NTNU). This was done as part of the weekly work sessions facilitated by EA NTNU, where all members of EA NTNU gather physically to work with separate projects. The evaluation revealed great results with members reporting that this way of learning about AI alignment in a meaningful context was more engaging, and thus more effective, given that the increased engagement made them invest more in the learning process. All members were very new to AI in general, making it reasonable to believe that anyone can undertake this project as long as they are willing to learn.

Our project group focused only on answering questions on Stampy’s Wiki, however, other groups may consider contributing to the development of Stampy as well. Here is a list of answers the group wrote for those that are curious: EA NTNU—Stampy’s Wiki. Additionally, the developers were inspired to make new features on seeing how people actually used the system.

Major thanks to plex for feedback on this post, and for helping out with the project description.