BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2025//speaker//NWAQCX
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2025-GURXPK@pretalx.com
DTSTART;TZID=CET:20250423T175000
DTEND;TZID=CET:20250423T182000
DESCRIPTION:The rise of LLMs has elevated prompt engineering as a critical 
 skill in the AI industry\, but manual prompt tuning is often inefficient a
 nd model-specific. This talk explores various automatic prompt optimizatio
 n approaches\, ranging from simple ones like bootstrapped few-shot to more
  complex techniques such as MIPRO and TextGrad\, and showcases their pract
 ical applications through frameworks like DSPy and AdalFlow. By exploring 
 the benefits\, challenges\, and trade-offs of these approaches\, the atten
 dees will be able to answer the question: is prompt engineering dead\, or 
 has it just evolved?
DTSTAMP:20260520T011405Z
LOCATION:Zeiss Plenary (Spectrum)
SUMMARY:Is Prompt Engineering Dead? How Auto-Optimization is Changing the G
 ame - Iryna Kondrashchenko\, Oleh Kostromin
URL:https://pretalx.com/pyconde-pydata-2025/talk/GURXPK/
END:VEVENT
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2025-LBKU3T@pretalx.com
DTSTART;TZID=CET:20250425T130500
DTEND;TZID=CET:20250425T143500
DESCRIPTION:Explore the inner workings of deep learning frameworks like Ten
 sorFlow and PyTorch by building your own in this workshop. We will start w
 ith the fundamental automatic differentiation mechanics and proceed to imp
 lementing more complex components like layers\, modules and optimizers. Th
 is workshop is mainly designed for experienced data scientists\, who want 
 to expand their intuition about lower level framework internals.
DTSTAMP:20260520T011405Z
LOCATION:Dynamicum
SUMMARY:What's inside the box? Building a deep learning framework from scra
 tch. - Oleh Kostromin
URL:https://pretalx.com/pyconde-pydata-2025/talk/LBKU3T/
END:VEVENT
END:VCALENDAR