AI Safety Poland Reading Club #5

​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.

We will talk about the Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback paper. For this meeting, we want you to read only the Introduction and Data Collection sections.