It would be great if you could post a google calendar link (maybe for the next event). That would make it a lot easier to figure time zone issues (I almost messed up due to our switch to summer time on March 28).
Regarding the suspension of the AstraZeneca vaccine: a crucial point I haven't seen mentioned is that the suspension is temporary: the AstraZeneca vaccinations were only suspended for four days. This is mentioned in the german FAQ that you linked (though presumably it was updated since you posted). In particular, EMA (the European Medicines Agency) recommended that vaccination be resumed on March 18, and the German Bund decided on the same day to resume vaccination on March 19th.
Also, not all EU countries halted vaccinations; my home country Austria for example continued using AstraZeneca.
It might well be that 1) people who already know RL shouldn't be much surprised by this result and 2) people who don't know much RL are justified in updating on this info (towards mesa-optimizers arising more easily).This would be the case if RL intuition correctly implies that proto-mesa-optimizers (like the one in the paper) arise naturally, and that intuition wasn't widely shared outside of RL. Not sure if this is actually the way things are, but it seems plausible to me.
Ah, gotcha, that makes more sense. And thanks for the awesome antigen test table you linked there!
Yeah, this has been confusing me as well. There's an antigen test that Roche claims has 96.52% sensitivity (so <4% false negatives), which seems both surprisingly high (since even PCR tests seem to have far lower sensitivity, as per the study you linked) and suspiciously precise.
Will the talk be recorded?
You might argue that each individual service must be dangerous, since it is superintelligent at its particular task. However, since the service is optimizing for some bounded task, it is not going to run a long-term planning process [...]
Does this assume that we'll be able to build generally intelligent systems (e.g. the service-creating-service) that optimize for a bounded task?
Is there a more recent writeup on the history of AI safety anywhere?