Juho Leinonen

Students using text prompts outperformed their peers using voice input, highlighting the need for careful consideration of input modalities in programming education.

Novice programmers often overlook crucial details in prompts, leading to a reliance on AI that can hinder their debugging skills and understanding of code generation.

Deliberately injecting bugs into GenAI-generated code significantly enhances students' debugging skills and success rates in subsequent attempts.

LLMs can get up to 6x more logically consistent without human feedback, simply by fusing NLI scores into the DPO training loop.

Forget hand-crafted examples: this system automatically generates worked examples tailored to student errors by mining common code patterns.

Open-weight language models can now mimic student debugging processes with surprising fidelity by learning from conversational logs of student-environment interactions, offering a privacy-respecting alternative to prompting proprietary LLMs.

Fine-tuning smaller, open-source LLMs on a targeted dataset can rival the performance of larger, proprietary models for explaining compiler errors, offering a cost-effective and privacy-preserving solution for educational tools.