BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Palaner//palaner Single Event//EN
METHOD:PUBLISH
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:luma-a082b5b76b@palaner.app
DTSTAMP:20260802T151048Z
DTSTART:20260813T010000Z
DTEND:20260813T023000Z
SUMMARY:Artificial Analysis: Inference\, Measured
DESCRIPTION:Saved in Palaner as: saved\n\nPalaner match: 17% · why: matches
  your usual pattern\n\nInference is the critical step that shapes the spee
 d\, cost\, and quality of every request your application makes. With new m
 odels releasing weekly\, the infrastructure landscape is moving just as fa
 st as the models themselves.\nChoosing an inference provider has many cons
 iderations including\, speed\, cost (incl. cache pricing discounts)\, late
 ncy\, and day zero support for new models.\nArtificial Analysis benchmarks
  over 500 inference endpoints across speed\, cost\, latency\, and quality.
  Our evaluations show output speeds for the same model vary by 15x across 
 providers. For the same query\, end-to-end response time can vary by up to
  12×\, while the cost difference between the cheapest and most expensive p
 rovider can exceed 3x.\nJoin the Artificial Analysis team for an evening w
 ith leaders across AI inference. We’ll examine the key inference trends\, 
 unpack what the benchmark data reveals\, and discuss what these difference
 s mean for those building with AI.\nAgenda:\n6:00 PM: Doors open\n6:30: Ar
 tificial Analysis talk\n7:00 PM: Panel\n7:30 PM: Networking\, light bites\
 , and drinks\n8:30 PM: Event ends\nSpeakers:\nTo be announced soon…👀\nPhot
 ography and videography disclaimer: By attending this event\, you acknowle
 dge that photography and videography may take place. If you do not consent
 \, please contact the event host.
URL:https://luma.com/0ukamlad
CATEGORIES:palaner,saved
STATUS:TENTATIVE
END:VEVENT
END:VCALENDAR