BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//sebbo.net//ical-generator//EN
NAME:Edison Public Library
X-WR-CALNAME:Edison Public Library
BEGIN:VEVENT
UID:959fd8f2-c612-44c4-bc53-caba78d2bdc7
SEQUENCE:0
DTSTAMP:20260917T054743Z
DTSTART;TZID=America/New_York:20261017T110000
DTEND;TZID=America/New_York:20261017T130000
SUMMARY:Introduction to AI Evaluations
LOCATION:North Edison Branch\nNorth Edison Branch
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=North Edison Branch;X-APPL
 E-RADIUS=10;X-TITLE=North Edison Branch:geo:40.5756994,-74.3589601
GEO:40.5756994;-74.3589601
DESCRIPTION: .\nhttps://edisonpubliclibrary.libnet.info/event/17423660
X-ALT-DESC;FMTTYPE=text/html:<p>This workshop pulls back the curtain on mo
 dern AI systems and explores the emerging field of AI evaluations (&ldquo\
 ;evals&rdquo\;): the methods researchers use to measure what these models 
 are capable of\, where they fail\, and how they might become dangerous.</p
 >\n<p><strong>Together\, we&rsquo\;ll tackle questions like:</strong></p>\
 n<p><strong>How are large language models actually created</strong>\, and 
 what distinguishes them from traditional software?</p>\n<p><strong>Reasoni
 ng</strong>&nbsp\;What is &ldquo\;chain-of-thought&rdquo\; reasoning\, and
  why are today&rsquo\;s models starting to behave in surprising ways?</p>\
 n<p><strong>Evals</strong>&nbsp\;What does safety testing for AI models ac
 tually look like?</p>\n<p><strong>Capabilities</strong>&nbsp\;How do resea
 rchers test for deception\, manipulation\, persuasion\, and autonomous beh
 avior?</p>\n<p><strong>What you&rsquo\;ll get:</strong></p>\n<ul>\n<li>A b
 eginner-friendly explanation of how modern AI systems function under the h
 ood&nbsp\;</li>\n<li>Hands-on demos where we simulate jailbreaks of differ
 ent AI models live and compare how they respond to attacks&nbsp\;</li>\n<l
 i>A walkthrough of real AI safety evaluations used by frontier labs</li>\n
 </ul>\n<p>Please note this is a hybrid event. Attendees are welcome to att
 end in person in Meeting Room #1 at the North Edison Branch or to join rem
 otely via&nbsp\;<a href="https://us06web.zoom.us/j/81259239262">Zoom</a>.<
 /p>\n<p>Open to adults. Registration is suggested but not required and beg
 ins October 5.</p>\n<p><em>About our partner</em></p>\n<p><em>The&nbsp\;AI
  Safety Awareness Project&nbsp\;is a 501(c)(3) nonprofit founded on the be
 lief that a safe AI future is one where the traditional pillars of U.S. so
 ciety have a seat at the table in deciding the direction of AI. The AI Saf
 ety Awareness Project (AISAP) want to be there for the first step: educati
 on and skills-building\, so that Americans have the necessary expertise an
 d awareness to direct our AI future. They run workshops and education prog
 rams for a variety of community groups and public institutions including l
 aw enforcement agencies\, libraries\, churches\, universities\, as well as
  the general public. AISAP partners with industry experts to inform organi
 zations about frontier AI research and developments\, including topics as 
 diverse as workforce augmentation and displacement\, AI agents and compani
 ons\, cybercrime\, AGI (Artificial General Intelligence)\, and loss of con
 trol risk.</em></p>\n<p><em>For more information about AISAP\, please visi
 t&nbsp\;https://aisafetyawarenessproject.org/&nbsp\;</em></p>\nhttps://edi
 sonpubliclibrary.libnet.info/event/17423660
URL;VALUE=URI:https://edisonpubliclibrary.libnet.info/event/17423660
ATTACH:https://static.libnet.info/images/events/edisonpubliclibrary/AISAP-
 logo.png
END:VEVENT
END:VCALENDAR