BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Superpower Daily//AI Events//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Superpower Daily AI events
BEGIN:VEVENT
UID:ca8f1794-254d-4f13-bfd0-f9e8f88a9690@superpowerdaily.com
DTSTAMP:20261120T200356Z
LAST-MODIFIED:20261120T200356Z
DTSTART:20261203T200000Z
DTEND:20261203T210000Z
SUMMARY:Enabling Frontier Models to learn from Open Ended\, Long Horizon Wo
 rk
DESCRIPTION:Joe Hakim\, Fig’s frontier data team lead\, will discuss why 
 open-ended\, real-world work is difficult for models to learn and how Fig 
 is developing new approaches to creating training environments. The talk w
 ill explore how each frontier model release expands the work models can co
 mplete autonomously.\nDetails: https://superpowerdaily.com/events/enabling
 -frontier-models-to-learn-from-open-ended-long-horizon-work-ca8f1794-254d-
 4f13-bfd0-f9e8f88a9690\nRegister: https://luma.com/9t33szn5
LOCATION:Online
URL:https://superpowerdaily.com/events/enabling-frontier-models-to-learn-fr
 om-open-ended-long-horizon-work-ca8f1794-254d-4f13-bfd0-f9e8f88a9690
STATUS:TENTATIVE
TRANSP:TRANSPARENT
END:VEVENT
END:VCALENDAR
