BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Larger and more instructable language  models become less reliable
   - José Hernández-Orallo Valencian Research Institute for  Artificial I
 ntelligence\, UPV Leverhulme Centre for the Future of  Intelligence\, ITH\
 , Cambridge
DTSTART:20241009T170000Z
DTEND:20241009T180000Z
UID:TALK222751@talks.cam.ac.uk
CONTACT:Alva Markelius
DESCRIPTION:At this year’s first CHIA Early Career Community Seminar\, J
 ose Hernandez Orallo will introduce his recent study published in Nature\,
  which reveals that\, as LLM families scaled up and shaped up\, their mode
 ls didn’t become more reliable. This seminar talk introduces some method
 ological innovations from \nthe perspective of AI evaluation.
LOCATION:Syndics Room\, 17 Mill  Lane
END:VEVENT
END:VCALENDAR