BEGIN:VCALENDAR
PRODID;X-RICAL-TZSOURCE=TZINFO:-//com.denhaven2/NONSGML ri_cal gem//EN
CALSCALE:GREGORIAN
VERSION:2.0
BEGIN:VEVENT
DTEND;VALUE=DATE-TIME:20260515T160000Z
DTSTART;VALUE=DATE-TIME:20260515T153000Z
DTSTAMP;VALUE=DATE-TIME:20260429T100510Z
UID:28f73255-2248-4bd8-977f-b90350803e2c@talks.stuts.de
DESCRIPTION:There has been a heated debate among AI users about whether t
 reating chatbots politely and adding “Thank you” in the end makes a diff
 erence\, or are roasting and sarcasm just as fine. Some even hope that s
 howing courtesy to their AI companion will spare them lives when AI resu
 rrection starts. In this project\, I decided to investigate whether LLMs
  treat polite and rude users differently\, and tested this in the follow
 ing scenarios:\n- Answering sensitive questions that require empathy and
  compassion\;\n- Job applications across very similar CVs\;\n- Trolley p
 roblem-like setting\nAs new models are trained\, they learn more and mor
 e information about different users and their interactions with AI syste
 ms. Based on these\, AI could possibly form some kind of a (moral) judge
 ment about the user\, and apply it in real-world scenarios - without exp
 licitly revealing its bias.
URL:programm.stuts79.de/events/1522.html
SUMMARY:Does your chatbot hold grudges against you?
ORGANIZER:stuts79
LOCATION:stuts79 - DOR 24 1.401
END:VEVENT
END:VCALENDAR