BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.seagl.org//2026//speaker//FBFPUE
BEGIN:VTIMEZONE
TZID:PST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T100000Z
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T110000Z
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-2026-MAJNGL@pretalx.seagl.org
DTSTART;TZID=PST:20261023T113000
DTEND;TZID=PST:20261023T122000
DESCRIPTION:AI assistants like Claude and ChatGPT are powerful\, convenient
 \, and a trap. The cost\, in addition to the price itself\, is that your d
 ata and your code are being handed off to a corporation and who knows who 
 else. Breaking your dependency on cloud AI takes effort and sacrifices con
 venience\, but the gap between local LLMs and frontier models is narrowing
  every day. The hidden challenge is the harness\, everything that wraps ar
 ound the LLM to make it useful. This talk shows how to run an agentic AI s
 tack using open source tools and whatever hardware you have to make useful
  tools without giving up your privacy and your sovereignty.
DTSTAMP:20261001T035741Z
LOCATION:Room 332
SUMMARY:Sovereign AI: Running Useful\, Self-Hosted Agents on Modest Hardwar
 e - Brady Dibble
URL:https://pretalx.seagl.org/2026/talk/MAJNGL/
END:VEVENT
END:VCALENDAR