Why AI Safety?

AI systems have the potential to massively benefit humanity. However, the development of these systems poses equally incredible risks. The risks posed are existential for the human species.

Ensuring any AI system’s goals are aligned with ours is a non-trivial task. Most notably, we only get one try to get this right.

What we do

We think that the best way to make progress on the problem of AI safety is getting more people to focus their careers on AI safety research, in fields like mechanistic interpretability, adversarial robustness, or AI governance.

Click here for our fellowship, and click here for our reading group. We also run projects.

Every month, we hold a general meeting (GM) in Haines Hall A20 where our project teams share their progress. GMs are open to literally everybody: no sign-up, just show up! Announcements are sent on our Discord.

Resources

As one of the foremost AI clubs at UCLA, we administrate the largest GPU server of any UCLA club. Members get access to train models on our GPUs (NVIDIA 3090s). Request access here.

Where we’ve been