AI Spring Amsterdam 🌸
A weekly reading group exploring the foundations of intelligence and the safety of AI systems.
Write to aispringamsterdam@outlook.com in order to join.
Write to aispringamsterdam@outlook.com in order to join.
Up Next
Next Session
📍 VU Amsterdam
Anthropic’s investigation into emotion-like representations and behaviors in large language models. Came up multiple times during our previous sessions, so we’re reading Parts 1 & 2 together.
Companion reading
The Adolescence of Technology — Dario AmodeiA bit unrelated with the paper this time, but coherent with the AI safety theme. A blog post by Anthropic's CEO discussing the risks of powerful AI.
How it works
Four themes, one cycle
We rotate through four themes every four weeks:
Foundation State of the Art Safety Free Topic
Each week
We read one paper + one companion piece (blog post, video, or essay), then meet in person for ~60–90 min of discussion over coffee. A rotating discussion lead prepares a small presentation.
Calendar