BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CityInEurope//Budapest//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:cmul62eft007gcd6u0rtduc7g@kesif
DTSTAMP:20260928T154800Z
DTSTART:20261001T150000Z
DTEND:20261001T170000Z
SUMMARY:Evals #4\, Miton AI Times edition
DESCRIPTION:**!We are starting one hour later!**\n\nMiton AI Times and [e
 vals.cz](http://evals.cz) have joined forces to prepare the next event.\
 n\nThis time it will be about evaluation\, evals.cz is a Prague meetup f
 or people who build AI products and need to measure them.\n\nModel bench
 marks are everywhere\, but what you care about is different: does it wor
 k for you\, on your data\, for your users?\n\n**Evelina Gabasova: The We
 ird and Wonderful World of Cybersecurity Evals**\n​*AI cybersecurity e
 vals have suddenly become a mainstream concern\, and the OpenAI/Hugging 
 Face incident shows benchmarks are now adversarial environments. In this
  talk\, we take a practical view of evaluating models for vulnerability 
 discovery and remediation. Using examples from AISLE’s work\, we’ll 
 discuss the problems with public benchmarks\, challenges in building our
  own\, and failure modes when the eval itself is the attack surface.*\n
 ​\n\nhttps://www.meetup.com/miton-times/events/316550499/
URL:https://www.meetup.com/miton-times/events/316550499/
LOCATION:Truhlárna Karlín\, Šaldova 388/5\, 180 00 Praha 8-Karlín\, P
 rague\, Prague
X-KESIF-URL:https://cityineurope.com/event/cmul62eft007gcd6u0rtduc7g
BEGIN:VALARM
TRIGGER:-PT2H
ACTION:DISPLAY
DESCRIPTION:Evals #4\, Miton AI Times edition
END:VALARM
END:VEVENT
END:VCALENDAR