AI Safety Readings

We run a regular reading group on AI Safety research. We discuss recent papers on interpretability, alignment, multi-agent safety, and related topics — from mechanistic interpretability to broader governance perspectives. Everyone is welcome, regardless of background.

The reading group is currently held on Mondays at 14:00 Copenhagen time. Email us at galke@imada.sdu.dk if you want to join or have any questions.

Schedule

Date	Topic	Presenter
Feb 3, 2026	Activation Oracles	Federico
Feb 10, 2026	Weird generalizations	Lukas
Feb 17, 2026	The Dead Salmons of AI Interpretability	Andor