[TAKEN] Vibe coding and meta-cognitive supports

Andrej Karpathy coined the phrase “vibe coding” to describe the development of software systems using chatbot-based tools supported by generative AI, instead of writing code. Suppose we were teaching vibe coding to learners with no prior coding experience. What might an educational vibe coding platform look like? In this second of two proposed projects on vibe coding, we … Read more

[TAKEN] Vibecoding and autograding

Andrej Karpathy coined the phrase “vibe coding” to describe the development of software systems using chatbot-based tools supported by generative AI, instead of writing code. Suppose we were teaching vibe coding to learners with no prior coding experience. What might an educational vibe coding platform look like? In this first of two proposed projects on vibe coding, we … Read more

[TAKEN] Off the rails? Exploring the effectiveness of generative AI “guardrails” for novice programmers

There is an argument that Generative AI tools (e.g. GitHub Copilot) are too helpful for novice programmers and might contribute to poor learning outcomes. Researchers and educators have been exploring the use of “guardrails” to constrain the output of these tools, for example, by providing guidance or analogous examples, rather than complete code. https://cs50.ai/ is … Read more

[TAKEN] ChatGDB

Debugging is challenging for novice programmers. This project will design, implement and evaluate a chat-based interface to assist novice programmers to orchestrate debugging sessions using a natural language interface, supported by generative AI. If desired, the Introduction to Computing modules at TCD (ARM Assembly Language programming) could provide context for the project.