BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2026//speaker//NYBL9E
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2026-S7KYEE@pretalx.com
DTSTART;TZID=CET:20260415T105500
DTEND;TZID=CET:20260415T112500
DESCRIPTION:Fairness is fundamentally not tractable to classic optimisation
  techniques. It's not a state of the world\, it's an experience of it. No 
 technology is fair in a vacuum - fairness can only be understood when a te
 chnical system collides with humans.\n\nWe're seeing a wave of off-the-she
 lf libraries measuring bad behaviours in LLM outputs\, often simplificatio
 ns of older fairness metrics. They can catch obvious failure modes like sl
 urs. But this is one failure mode among many. Installing a library and cal
 ling the job done is fairness washing. The harder\, more fruitful approach
  is to explore the space of failure modes\, consider what an ideal world w
 ould look like\, and design measures\, mitigations\, and feedback loops ac
 cordingly.\n\nThis is a talk for people who suspect we can't optimise our 
 way to human dignity.
DTSTAMP:20260412T142007Z
LOCATION:Palladium [2nd Floor]
SUMMARY:No\, you can't 'eval' your way to fairness - Laura Summers
URL:https://pretalx.com/pyconde-pydata-2026/talk/S7KYEE/
END:VEVENT
END:VCALENDAR