What we're about

Notice: We decided to not host meetups in the next months. Tom wants to set more time aside to self-study Deep Learning and Remmelt for organising the next AI Safety Camp. (http://AISafety.Camp)

We've been enjoying one-on-one distanced walks in nature though. If you'd enjoy going on a walk (and have no flu symptoms), particularly to talk about study stuff, do reach out! Calls also work.

You can email Tom here: tlieberum{at}outlook[dot]de
Or plan a moment with Remmelt: http://calendly.com/remmelt/30min/
We are a group mostly consisting of students and beginning researchers in artificial intelligence. We are interested in how to build safe artificial intelligence and regularly have reading meetups with in-depth discussions about this. Papers and blog-posts we discussed so far were about the following:

- Expert predictions about the arrival of artificial general intelligence.

- The "Concrete Problems in AI Safety" paper. In particular:

- Negative side-effects in reinforcement learning and solution attempts through "Relative Reachability".

- The "Agent Foundations" framework of the Machine Intelligence Research Institute.

Join our in-depth reading meetups for people interested in working on aligning algorithms with human values.

Past events (15)

Iterated Distillation and Amplification

Online event

Discussion on Mesa Optimization

Online event

Discussion on Comprehensive AI Services

Online event

Photos (10)