Course description
One major use-case for Large Language Models (LLMs) is assisting in, or taking over, writing computer code. To achieve this one can ask for computer code in a chatbot. Alternative methods are having your IDE (Integrated Development Environment, usually the program one writes code in) connected to an LLM. This way, the LLM can assist in the production of code to produce some of it, or even all of it entirely.
In this workshop, we will show how Visual Studio Code with a plugin (Roo Code) can be used enable production of code assisted by, or done entirely, by an LLM. We will use both local models, as well as gpt.uio.no (UiO's version of ChatGPT from OpenAI) through its API access. Use cases will be generating small programs, as well as writing code to do simple data analysis, visualizations, and executing and interpreting the analysis.
The main programming language used will Python, but the setup can also be used to produce and run code in other languages.
Target audience
Researchers in any scientific field that work with data(files) and/or write computer programs (in any language).
Learning outcomes
After the workshop, learners:
- Will be able to use an LLM connected through Visual Studio Code to write computer code and execute it
- Will know the benefits of efficiently prompting the LLM, and the iterative process to obtain a functioning program
- Will be able to discuss ethical and practical considerations when using LLM-based tools in scientific research
Prerequisites
- Intermediate / Advanced level
- Experience with Python programming or a similar programming language.
- Experience with using Visual Studio Code for working with code.
- A laptop with administrator access.
- A more recent laptop is needed to run models locally, while API access to gpt.uio.no (or ChatGPT from OpenAI, or similar LLMs) can make the setup work for everyone.
- Knowing the basics of version control is a benefit.
- Knowing the basics of LLMs and their usage is a benefit but not an absolute requirement.
Technical and Material Requirements
- Laptop with Visual Studio Code installed, and with administrator access.
Lunch
- There will be a complementary buffet-lunch at 12:00-13:00 from the Sverdrups spiseri (Georg Sverdrups Hus, 2nd floor).
- After you get your lunch, join us at Store møterom where we have reserved seats for #DSDays2026 participants.
Number of participants
After the soft deadline, a waiting list will be automatically handled upon de-registrations.
Contact
If you have any questions regarding this course, or anything else about the DSDays 2026 event, please contact us per email: digitalscholarship@ub.uio.no