As part of the fellowship that I announced back in September, the fellows and I will be hosting an online event to talk about our research! Tentative schedule:

• Alex_Altair: What is a world model?
• Daniel C: Towards building blocks of ontologies
• José Pedro Faustino: Agent Structure Problem and Internal Model Principle
• Alfred Harwood: Does Agent-like behaviour generalize?
• Dalcy Ku: Thoughts on Structural Selection Theorems

The talks will be informal, and the scope is anything in technical AI safety that we are interested in. Questions and discussion will be encouraged! Topics are likely to include: world models, information theory, ontology identification, and SLT.

Click here for the google calendar.