The Friendly AI Problem: how can we ensure that superintelligent AI doesn't terminate us?
Venue: Room 416, Birkbeck College.
Date: Saturday 23rd January.
About the talk:
Suppose that humans succeed in understanding just what it is about the human brain that makes us smart, and manage to port that over to silicon based digital computers. Suppose we succeed in creating a machine that was smarter than us.
What would it do? Would we benefit from it?
This talk will present arguments that show that there are many different ways that the creation of human-level AI could spell disaster for the human race. It will also cover how we might stave off that disaster - how we might create a superintelligence that is benevolent to the human race.
About the speaker:
Roko Mijic graduated from the University of Cambridge with a BA in Mathematics, and the Certificate of Advanced Study in Mathematics. He spent a year doing research into the foundations of knowledge representation at the University of Edinburgh and holds an MSc in informatics. He is currently an advisor for the Singularity Institute for Artificial Intelligence.
Roko writes the blog "Transhuman goodness"
For more details about Roko, see RokoMijic.com
** There's no charge to attend this meeting, and everyone is welcome. There will be plenty of opportunity to ask questions and to make comments.
**Discussion will continue after the event, in a nearby pub, for those who are able to stay.
** Why not join some of the Extrobritannia regulars for a drink and/or light lunch beforehand, any time after 12.30pm, in The Marlborough Arms, 36 Torrington Place, London WC1E 7HJ. To find us, look out for a table where there's a copy of the book "Beyond AI: creating the conscience of the machine" displayed.
Room 416 is on the fourth floor (via the lift near reception) in the main Birkbeck College building, in Torrington Square (which is a pedestrian-only square). Torrington Square is about 10 minutes walk from either Russell Square or Goodge St tube stations