We invite everyone with a technical interest in AI safety to a get-together in the Bayesment (see below) on Saturday, January 7th 16:00 - 20:00. Sign up here.
We’re looking forward to meeting everyone with an interest in AI safety research, no matter whether you’re just getting started or already working in the field. After the intro round (which starts 16:30) we expect we’ll be talking about prerequisites, approaches and current developments. In particular: What’s the path for engaged people to start contributing usefully?
To give focus to the meeting we’d like to exclude discussion of “is AI safety a problem?”.
We will probably be ordering dinner.
Best, Dima and Christian
[1] Hafenplatz 5, 10963 Berlin, near S Anhalter Bahnhof and U Mendelssohn-Bartholdy-Park, Doorbell says Schreiber / Wissemann, 5th floor and to the right