AI Safety Poland Reading Club #14

​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.

This time, we will take a look at the Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident by METR and Redwood Research.

​We plan to go through the entire thing in a single meeting, so just skim the contents and try to get a general overview of the findings.