AI Safety Poland Reading Club #1

​Who should come: Anyone interested in AI safety, machine learning research, or the broader societal impacts of AI systems.

What it's about: We'll read and discuss influential papers in AI safety research. Read the paper beforehand, show up, and talk through the ideas, questions, and disagreements it raises.

First paper: Concrete Problems in AI Safety (Amodei et al., 2016)
https://arxiv.org/pdf/1606.06565

​This paper identifies five practical problems that could lead to unintended harmful behavior in real-world AI systems: avoiding side effects, avoiding reward hacking, scalable supervision, safe exploration, and distributional shift. How it looks after 10 years of developments in the field?