BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pydata-london-2026//talk//XQXNVK
BEGIN:VTIMEZONE
TZID:GMT
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pydata-london-2026-XQXNVK@pretalx.com
DTSTART;TZID=GMT:20260607T133000
DTEND;TZID=GMT:20260607T141500
DESCRIPTION:Large language models (LLMs) have taken the world by storm sinc
 e the public launch of ChatGPT 3 in November 2022\, sparking a huge number
  of LLM-powered tools\, products and start-ups. Since then LLMs have gaine
 d reasoning and tool use capabilities\, and have been integrated into more
  autonomous agentic workflows\, leading to significant increases in their 
 usefulness for software engineering work. However\, despite being readily 
 accessible to us all\, these models and their agentic wrappers remain blac
 k boxes to many of us using them in our daily work.\n\nMartin will demysit
 ify LLMs by providing an intuitive understanding of how they build upon ke
 y prior advances to successfully cross the "uncanny valley" of text genera
 tion and achieve almost flawless fluency. He will explain what makes these
  models "foundational"\, illustrating how this "one weird trick" of next w
 ord prediction results in models that can be easily fine-tuned for convers
 ation\, coding and reasoning\, and we'll take a peek under the hood of how
  LLMs have been extended to integrate private data sets\, call external to
 ols and support more autonomous agentic workflows.  \n\nThis talk won't ma
 ke you an expert on deep neural networks\, transformers\, fine-tuning or a
 gentic workflows\, but it will give you a peek behind the curtain of how t
 hese seemingly magical models work and hopefully give you enough intuitive
  understanding to explain them to friends and family.
DTSTAMP:20260602T223426Z
LOCATION:Grand Hall 1
SUMMARY:Keynote- Martin O'Reilly- LLMs and AI agents demystified - Martin O
 'Reilly
URL:https://pretalx.com/pydata-london-2026/talk/XQXNVK/
END:VEVENT
END:VCALENDAR