AI Safety Poland Reading Club #9

​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 go through a requested recent research paper, namely Natural Language Autoencoders from Anthropic. For the next meeting, please read:

• ​https://www.anthropic.com/research/natural-language-autoencoders (a short and accessible introduction)

• ​https://transformer-circuits.pub/2026/nla (the actual paper) - up to (and including) the Case Studies section