Tag
This study compares two LLM-based tutoring approaches (Socratic guidance vs prompt refinement) for programming education, finding that Socratic guidance fosters better learning outcomes and more understanding-driven prompting strategies when students later use unconstrained LLMs.
Highlights Andrej Karpathy's free three-hour YouTube course covering LLM fundamentals, including tokenization, neural network internals, RLHF, and reinforcement learning. Emphasizes that understanding these core architectural principles offers major career advantages over simply knowing how to use off-the-shelf AI tools.
This paper presents WriteFlow, an AI voice-based writing assistant designed to support reflective academic writing through goal-oriented interaction, addressing limitations of efficiency-focused writing tools by scaffolding metacognitive regulation and goal articulation. Findings from a Wizard-of-Oz study with 12 expert users demonstrate that the system effectively supports iterative goal refinement and goal-text alignment during the drafting process.