AI could bring huge benefits
if we avoid its enormous risks

AI might cause the biggest technological leap in human history this century. Who is making sure that this will go well?

We are a group of students and researchers working towards the long-term safety of artificial intelligence. Our goal is to help ensure that future powerful AI systems are safe.

The Bern AI Safety (BAIS) Group meets regularly to discuss topics in AI alignment and AI safety, with a general focus on the technical aspects and implications of such topics. Additionally, we also organize workshop meetings where people meet and discuss project ideas, as well as anything else they are interested in.

What are we doing?

Anyone interested in promoting the safe development of AI, whether from a technical or policy perspective, is welcome to join us. Our community includes both students and researchers.

Who is this for?

Next Events

Introduction Event Spring 2024
https://lu.ma/kmip223b

"You can't fetch the coffee if you're dead."

— Prof. Stuart Russel

All agents possess a self-preservation drive that compels them to strive for survival, leading to the emergence of behaviours like deception and power-seeking. If such behaviours arise in a highly advanced artificial intelligence, it poses a grave existential threat to humanity.

  • Leander

    MSc Data Science

  • Hannes

    Independent AI Researcher
    Programming Enthusiast

Let’s meet up and talk about AI.