BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Summit//Schedule//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:your-evals-are-lying@summit.xocoweb.workers.dev
DTSTAMP:20261108T084720Z
DTSTART:20270610T104000Z
DTEND:20270610T112000Z
SUMMARY:Your evals are lying to you: measuring models on real work
DESCRIPTION:Elif Demir\n\nPublic benchmarks say models are nearly perfect at analysis. A benchmark built from real company data says otherwise. Elif Demir on what it takes to measure models honestly.
LOCATION:Studio\, Armazém 7\, Doca de Alcântara\, Armazém 7\, 1350-352 Lisboa\, Portugal
URL:https://summit.xocoweb.workers.dev/sessions/your-evals-are-lying/
END:VEVENT
END:VCALENDAR