BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Ambitious Value Learning - Adrià Garriga Alonso (University of Ca
 mbridge)
DTSTART:20190213T170000Z
DTEND:20190213T190000Z
UID:TALK120277@talks.cam.ac.uk
CONTACT:Adrià Garriga Alonso
DESCRIPTION:This week we read the "Ambitious Value Learning" series by Roh
 in Shah (and others). This is the introduction and posts under "Ambitious 
 Value Learning" at https://www.lesswrong.com/s/4dHMdK5TLN6xcqtyc . You sho
 uld read it before the session.\n\nAmbitious value learning is the "tradit
 ional" AI safety research agenda: attempting to learn (or write down) all 
 of human values\, to later give them to an AI to maximise. If you think of
  your AI as long-term goal-oriented\, this is almost the only way to solve
  the problem. In this series of posts Rohin challenges this problem framin
 g\, arguing that we may need to step out of it in order to implement safe 
 AGI. The first part describes this framing\, and some of the problems that
  have been found in it over the years.\n\nAs usual\, there will be free pi
 zza. The first half hour is for stragglers to finish reading.\n\nInvite yo
 ur friends to join the mailing list (https://lists.cam.ac.uk/mailman/listi
 nfo/eng-safe-ai)\, the Facebook group (https://www.facebook.com/groups/107
 0763633063871) or the talks.cam page (https://talks.cam.ac.uk/show/index/8
 0932). Details about the next meeting\, the week’s topic and other event
 s will be advertised in these places.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR