LFU:online

Upon successful completion of the course, students will be able to use large language models (LLMs) to enhance their proficiency in Python programming. Specifically, they will:

• Describe the basics of LLMs’ architecture and prompt engineering.
• Use LLMs for personalized tutoring and interactive learning.
• Modify AI-generated solutions to improve code quality.
• Outline productivity aspects of various frameworks and their impact on programming tasks.
• Recognise human-AI collaboration and best practices to prepare for changes in the job market.

The course is designed to equip students with the skills to integrate large language models (LLMs) into their (Python) programming. The course focuses on Python, but the skills can be applied for other programming languages. The course will cover the following topics to achieve defined learning outcomes.

Introducing the Basics: The goal is to comprehend the architecture of LLMs and the principles of prompt engineering, enabling students to analyze how LLMs handle natural and formal languages. Practical exercises will facilitate their ability to apply these concepts to examples involving English and mathematical notation.

Tutoring Strategies: The goal is to understand how LLMs can facilitate interactive and personalized learning in Python programming. Students will learn to use LLMs to analyze code, interpret syntax and semantics, and address error messages through their interpretation and debugging suggestions. They will also design prompts to receive hints rather than direct answers, and leverage LLMs to create additional questions and tasks to reinforce learning of the key concepts.

Refining Outcomes: The goal is to refine AI-generated programs through an iterative approach. This involves defining and generating test cases, creating comprehensive documentation, and refactoring code to improve readability (making the code easier to understand), testability (simplifying the identification of faults in the code), and performance (boosting the effectiveness of the program). Students will also engage with LLMs to discuss and select appropriate data types, functions, and packages.

Increasing Productivity: The goal is to evaluate the impact of LLMs on programming productivity. Students will learn about claims regarding efficiency improvements in software development and explore various frameworks with different levels of customization and integration into programming environments. Students will analyze how these frameworks influence productivity across different stages of programming.

Exchanging Experiences: The goal is to explore and evaluate different setups–AI-only, hybrid, and human-only–to identify the opportunities, challenges, and risks of human-AI collaboration. Students will discuss lessons learned, best practices, and tools, aiming to develop strategies for adapting to upcoming changes in the job market.

The course provides activities to convey theoretical knowledge and practical skills. After a presentation by the lecturer, students work alone or in teams to apply their new skills on given or their own examples under the supervision of the lecturer.

Course assessment is based on a regular contribution by participants instead of examinations. There are no grades, only a note on “successfully completed” (de: Mit Erfolg teilgenommen) or “not completed” (de: Ohne Erfolg teilgenommen) course. Further assessment details will be provided in the first unit.

To be announced at the beginning in the first session.

None. This course is dedicated to students who have no or intermediate-level programming skills (in Python). While requesting booking in the course, please add a comment including your proficency level in particular programming languages.

Disclaimer: This course focuses on understanding AI-supported learning and programming approaches without teaching actual programming skills. However, knowledge and skills from the course can be applied to self-learn programming with support of generative AI.