BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.balticnog.org//KLRJXV
BEGIN:VTIMEZONE
TZID:EET
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=19991231T220000Z
TZNAME:EET
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:STANDARD
BEGIN:STANDARD
DTSTART:20011028T050000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:EET
TZOFFSETFROM:+0300
TZOFFSETTO:+0200
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20010325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:EEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bnog-2026-KLRJXV@pretalx.balticnog.org
DTSTART;TZID=EET:20260924T120000
DTEND;TZID=EET:20260924T122500
DESCRIPTION:AI networking discussions often stop at the GPU cluster. But a 
 single inference task may increasingly cross devices\, agents\, models\, t
 ools\, data sources\, networks and providers—turning one user interactio
 n into a dynamic distributed execution graph.\n\nThis talk explores what t
 hat could mean for network architecture and interconnection. It examines h
 ow latency\, compute availability\, policy and state may influence where p
 arts of a task execute\, and why explaining performance becomes difficult 
 across organisational boundaries.\n\nIt maps existing observability buildi
 ng blocks and introduces FOX\, a deliberately exploratory model for exchan
 ging selected\, policy-controlled evidence. The talk concludes by connecti
 ng observability with security and resilience\, including agentic amplific
 ation\, inference exhaustion\, hidden dependencies and stateful failover.
DTSTAMP:20260920T211041Z
LOCATION:ROOM ALFA
SUMMARY:Beyond the GPU Cluster: Building Networks for Distributed AI Infere
 nce - Kaj Kjellgren
URL:https://pretalx.balticnog.org/bnog-2026/talk/KLRJXV/
END:VEVENT
END:VCALENDAR