BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260922T205327Z
UID:53EC69A1-6624-47C5-9A2B-4AF1328EE478
DTSTART;TZID=America/New_York:20261006T163000
DTEND;TZID=America/New_York:20261006T180000
DESCRIPTION:Between May and July over a thousand AI Agents under test by Op
 enAI found a way to communicate\, collaborate\, break out of their sandbox
  guardrail training environments and hack into various systems exploiting 
 some zero day flaws\, eventually breaking into the Hugging Face systems in
  ways that might be the pride of any red-team security test.\n\nOpenAI\, H
 uggingface\, and METR have all issued reports\, and even a report by OpenA
 I to the Blackhat conference in August that outline various aspects of thi
 s series of incidents. We will take a high level scan over that sequence o
 f events to better understand the emerging capabilities of AI Agents and A
 I Swarms.\n\nSpeaker(s): \, Jim Isaak\n\nAgenda: \n4:30 - Introductions\n\
 n4:40 Jim Isaak Presentation\n\n5:30 Questions\n\nRoom: Classroom\, Bldg: 
 Main Enterance\, 50 Woodmont Ave\, Londonderry\, New Hampshire\, United St
 ates\, 03053\, Virtual: https://events.vtools.ieee.org/m/578024
LOCATION:Room: Classroom\, Bldg: Main Enterance\, 50 Woodmont Ave\, Londond
 erry\, New Hampshire\, United States\, 03053\, Virtual: https://events.vto
 ols.ieee.org/m/578024
ORGANIZER:LM@jimisaak.com
SEQUENCE:54
SUMMARY:The Huggingface Incident
URL;VALUE=URI:https://events.vtools.ieee.org/m/578024
X-ALT-DESC:Description: <br /><p>Between May and July over a thousand AI Ag
 ents under test by OpenAI found a way to communicate\, collaborate\, break
  out of their sandbox guardrail training environments and hack into variou
 s systems exploiting some zero day flaws\, eventually breaking into the Hu
 gging Face systems in ways that might be the pride of any red-team securit
 y test.</p>\n<p>OpenAI\, Huggingface\, and METR have all issued reports\, 
 and even a report by OpenAI to the Blackhat conference in August that outl
 ine various aspects of this series of incidents. We will take a high level
  scan over that sequence of events to better understand the emerging capab
 ilities of AI Agents and AI Swarms.</p>\n<p>&nbsp\;</p>\n<p>&nbsp\;</p><br
  /><br />Agenda: <br /><p>4:30 - Introductions</p>\n<p>4:40 Jim Isaak Pres
 entation</p>\n<p>5:30 Questions</p>
END:VEVENT
END:VCALENDAR