Registration is closed for the event requested
Computational Modelling with Single Prompts
#AI
#Computational
#Modelling
#Single
#Prompts
#WIE
Regardless of how we look at AI large language models (LLMs) - as a massive collection of data
from which we can cleverly extract information, as an assistant who can perform simple tasks for us
and write simple codes, or perhaps as a machine that randomly selects words, in a sense guided by
what it have had has seen in the past - we are undoubtedly witnessing a revolution.
In the seminar, I will discuss selected aspects of the use of modern large language models, such as
Gemini, Grok, ChatGPT, DeepSeek, and Claude. I will discuss the concept of a single prompt and its
use to generate computer code for dozens of models across computational physics, statistical physics,
computational fluid dynamics, including LBM and more. I will illustrate the presentation with
practical examples of how language models generate code for research in computational physics,
thereby saving several days of work for an experienced programmer and, moreover, opening new
perspectives in research in computational sciences.
Date and Time
Location
Hosts
Registration
Add Event to Calendar
Speakers
Dr. hab Maciej Matyka of Division of Applied Computer Science and Statistical Physics, Institute of Theoretical Physics, Department of Physics and Astronomy,University of Wroclaw
Topic:
Computational Modelling with Single Prompts
Regardless of how we look at AI large language models (LLMs) - as a massive collection of data
from which we can cleverly extract information, as an assistant who can perform simple tasks for
us and write simple codes, or perhaps as a machine that randomly selects words, in a sense
guided by what it have had has seen in the past - we are undoubtedly witnessing a revolution.
In the seminar, I will discuss selected aspects of the use of modern large language models,
such as Gemini, Grok, ChatGPT, DeepSeek, and Claude. I will discuss the concept of a single
prompt and its use to generate computer code for dozens of models across computational physics,
statistical physics, computational fluid dynamics, including LBM and more. I will illustrate
the presentation with practical examples of how language models generate code for research in
computational physics, thereby saving several days of work for an experienced programmer and,
moreover, opening new perspectives in research in computational sciences.
Biography:
Maciej Matyka, born in 1980 in Wrocław. Computer physicist, programmer. Graduate of computer
physics at the Faculty of Physics and Astronomy, University of Wroclaw, where he is currently a
research and teaching fellow at the Institute of Theoretical Physics. His professional interests
include fluid flow through porous media and computer simulation methods. He independently programs
algorithms he has developed and is a practitioner.
He enjoys projects and working with students. He is also interested in programming and new
technologies in computer science - parallel computing and machine learning. He has always had a
passion for graphics and animation based on physical modelling, which he uses on computer
demoscene. He is the author of numerous scientific publications in computational physics and
fluid dynamics, two stand-alone books (including a book on computer simulations)
and several chapters in books published in Poland and abroad.
Address:Division of Applied Computer Science and Statistical Physics, Institute of Theoretical Physics, Department of Physics and Astron, University of Wroclaw, Wroclaw, Poland