School of Computer Science and Statistics
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
I would be happy to discuss proposals for any student project broadly related to programming education (any programming language). I am particularly interested in projects that explore the potential to use AI coding assistants (e.g. GitHub Copilot) to support teaching and learning, as well as projects that explore the impact of the use of AI … Read more
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
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
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.
The organization VoteWatch collected data for the European Parliament (EP) over the years 2014 – 2019. The data contain multiple information on the items being voted by the members of parliament (MPs) over that period, such as the area of a policy, the legal classification of the document being voted, etc. The aim of this … Read more
Due to the potential damage a cryptrographically relevant quantum computer could do to uses of widely used asymmetric cryptographic algorithms, a range of new “post-quantum” algorithms have been developed and are being widely deployed, e.g. in TLS in web browsers. This project is to investigate potential timing issues with implementations of such algorithms, likely reproducing … Read more
In network modelling, edges are inherently interdependent: for instance, if you express interest in this project and contact me, it is more likely that a friend of yours, specifically one who shares similar interests and studies mathematics, will do the same. This interdependence complicates the statistical modelling of relational data, such as email communication networks. … Read more
In this project we are exploring non-parametric methods for the estimation of probability density functions and for regression. The interested Student must be comfortable with Statistics and Mathematics. The Student must do a search about kernel density estimation and Nadaraya–Watson kernel regression. You may also have a look in Prof. Tsybakov’s book “Introduction to nonparametric … Read more
This project is particularly for the Students in Statistics and Sustainability. The interested Student should first check the papers: Establishing the link: Does web traffic from various marketing channels influence direct traffic source purchases? | Marketing Letters (springer.com) Unveiling digital dynamics: Do digital media investments impact organic branded searches? | Journal of Marketing Analytics The … Read more