BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.iacapconf.org//iacap-2026//talk//9YLPZK
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:DAYLIGHT
DTSTART:20250715T000000
TZNAME:CDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T020000
RDATE:20261101T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20270314T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Trustworthy AI and the King Midas Problem - Thomas Mitchell
DTSTART;TZID=US/Central:20260715T171000
DTEND;TZID=US/Central:20260715T174000
DTSTAMP:20260726T081835Z
UID:pretalx-iacap-2026-9YLPZK@pretalx.iacapconf.org
DESCRIPTION:The King Midas Problem concerns the possibility that we may gi
 ve a highly advanced AI instructions intended for our benefit\, but\, like
  King Midas wishing for all he touched to turn to gold\, realise too late 
 that there are severely harmful consequences to our wishes being fulfilled
 . A classic example is Nick Bostrom’s paperclip maximiser\, in which an 
 AI\, having been instructed to maximise the manufacture of paperclips\, tu
 rns everything it can into paperclips\, effectively destroying the planet 
 in the process.\n\nI propose a solution based on the observation that the 
 King Midas Problem is an instance of the Principal-Agent Problem. The solu
 tion crucially involves the concept of trustworthy AI. What is more\, I ar
 gue that the problem cannot be solved without making AI trustworthy. This 
 means that\, contrary to the opinion of many writers on the topic\, trustw
 orthiness must be considered alongside other important factors\, like safe
 ty and reliability\, in the development of future highly advanced AIs.
LOCATION:Executive Conference Room
URL:https://pretalx.iacapconf.org/iacap-2026/talk/9YLPZK/
END:VEVENT
END:VCALENDAR