BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Jason Rute (IBM Research)
DTSTART:20250115T150000Z
DTEND:20250115T153000Z
DTSTAMP:20261023T041633Z
UID:LeanTogether2025/2
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/LeanTogether
 2025/2/">The last mile: How do we make AI theorem provers which work in th
 e real world for real users and not just on benchmarks?</a>\nby Jason Rute
  (IBM Research) as part of Lean Together 2025\n\n\nAbstract\nAs AI researc
 h progresses\, we are seeing massive gains on formal math benchmarks like 
 MiniF2F and challenges like the IMO.  However\, these gains are not direct
 ly accessible to the typical ITP user\, nor are they used to build formal 
 mathematical libraries.  Is this because the technology is not as good as 
 promised or because there is a disconnect between research and the day-to-
 day needs of users?  I propose that even today\, we have sufficient AI tec
 hnology to enhance the experience of proof assistant users significantly. 
  I approach this from the lens of product-focused software engineering.  H
 ow do we bridge “the last mile” to make a useful product for the end u
 ser?\n
LOCATION:https://researchseminars.org/talk/LeanTogether2025/2/
END:VEVENT
END:VCALENDAR
