BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Denver
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:MDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260318T231526Z
UID:10CB3D6B-2272-4F69-90CB-6318E2B3DE06
DTSTART;TZID=America/Denver:20260318T120000
DTEND;TZID=America/Denver:20260318T130000
DESCRIPTION:Regardless of how we look at AI large language models (LLMs) - 
 as a massive collection of data\nfrom which we can cleverly extract inform
 ation\, as an assistant who can perform simple tasks for us\nand write sim
 ple codes\, or perhaps as a machine that randomly selects words\, in a sen
 se guided by\nwhat it have had has seen in the past - we are undoubtedly w
 itnessing a revolution. In the seminar\, I will discuss selected aspects o
 f the use of modern large language models\, such as\nGemini\, Grok\, ChatG
 PT\, DeepSeek\, and Claude. I will discuss the concept of a single prompt 
 and its\nuse to generate computer code for dozens of models across computa
 tional physics\, statistical physics\,\ncomputational fluid dynamics\, inc
 luding LBM and more. I will illustrate the presentation with\npractical ex
 amples of how language models generate code for research in computational 
 physics\,\nthereby saving several days of work for an experienced programm
 er and\, moreover\, opening new\nperspectives in research in computational
  sciences.\n\nSpeaker(s): \, Dr. hab Maciej Matyka\n\nVirtual: https://eve
 nts.vtools.ieee.org/m/546896
LOCATION:Virtual: https://events.vtools.ieee.org/m/546896
ORGANIZER:makaruk@hughes.net
SEQUENCE:25
SUMMARY:Computational Modelling with Single Prompts
URL;VALUE=URI:https://events.vtools.ieee.org/m/546896
X-ALT-DESC:Description: &lt;br /&gt;&lt;pre class=&quot;vC7TJ allowTextSelection&quot;&gt;&lt;span s
 tyle=&quot;font-size: 14pt\;&quot;&gt;Regardless of how we look at AI large language mo
 dels (LLMs) - as a massive collection of data &lt;br&gt;from which we can clever
 ly extract information\, as an assistant who can perform simple tasks for 
 us &lt;br&gt;and write simple codes\, or perhaps as a machine that randomly sele
 cts words\, in a sense guided by &lt;br&gt;what it have had has seen in the past
  - we are undoubtedly witnessing a revolution.\nIn the seminar\, I will di
 scuss selected aspects of the use of modern large language models\, such a
 s &lt;br&gt;Gemini\, Grok\, ChatGPT\, DeepSeek\, and Claude. I will discuss the 
 concept of a single prompt and its &lt;br&gt;use to generate computer code for d
 ozens of models across computational physics\, statistical physics\, &lt;br&gt;c
 omputational fluid dynamics\, including LBM and more. I will illustrate th
 e presentation with &lt;br&gt;practical examples of how language models generate
  code for research in computational physics\, &lt;br&gt;thereby saving several d
 ays of work for an experienced programmer and\, moreover\, opening new &lt;br
 &gt;perspectives in research in computational sciences.\n&lt;/span&gt;&lt;/pre&gt;
END:VEVENT
END:VCALENDAR