Discussion article for the meetup : Second MIRIxLosAngeles Meeting
The second MIRIxLosAngeles meeting will be held on Saturday, June 14, at 10:00 AM. The location will be the same as last time:
USC Institute for Creative Technologies
12015 Waterfront Drive
Playa Vista, CA 90094-2536.
If you would like to join us, please let me know, so I can know to expect you and give you necessary contact information. Due to the primary interests of the organizers, and some recent results I have to share, I expect for us to focus on the questions of "How should an agent assign probabilities to logical statements?" and "How should an agent assign probabilities to statements about his own probability function?" However, I expect that other people will come and direct the conversation in other useful directions, so it is hard to predict.
Experience in artificial intelligence will not be at all necessary, but experience in mathematics probably is. If you can follow the MIRI publications, you should be fine.
This event will be in the spirit of collaboration with MIRI, and will attempt to respect their guidelines on doing research that will decrease, rather than increase, existential risk. As such, practical implementation questions related to making an approximate Bayesian reasoner fast enough to operate in the real world will not be on-topic. Rather, the focus will be on the abstract mathematical design of a system capable of having reflexively consistent goals, preforming naturalistic induction, et cetera.
Food and refreshments will be provided for this event, courtesy of MIRI.
If you are not local to Los Angeles, you may want to consider hosting your own MIRIx event. You can find more information about this here.