Hands-On Prompt-Tutorials for Using GenAI in Research and Education
Turning a research paper into a clear and well-structured conference presentation is a familiar challenge in academic work. In this post, we test whether NotebookLM can generate a usable slide deck directly from an uploaded article. The focus is on how effectively the system translates a dense written argument into
Generative AI tools designed specifically for academic research are beginning to reshape how scholars conduct literature reviews and map scholarly debates. In this post, we test LeapSpace (ScienceDirect AI), Elsevier’s Scopus-integrated deep research assistant, to examine how it structures evidence, organises themes, and traces citation networks within peer-reviewed literature.
When using generative AI for legal research, the language of the prompt may influence not only stylistic features of the output but also the model’s underlying source selection. In this experiment, we examined how two advanced models – Claude Opus 4.6 and GPT-5.2 – responded to identical questions about
Generative AI tools are increasingly moving beyond static text responses towards richer, interface-driven explanations. In this post, we explore Gemini’s Dynamic View feature using a conceptually demanding technical question about transformer architectures. Rather than producing a conventional paragraph-style summary, Gemini generated an interactive, visually structured learning environment that allows
Claude Code is Anthropic's command line-integrated agent that runs directly on your computer, enabling terminal-based interactions with local files and applications. While the name suggests technical complexity, Claude Code is surprisingly accessible—offering the same conversational interface as chat-based models, but with the ability to execute code and
As AI image generation tools become increasingly sophisticated, the ability to distinguish between AI-generated and authentic photographs has emerged as a critical challenge. Platforms like Winston.AI and AI or Not claim to address this need by detecting synthetic imagery with high accuracy. But how well do these detection systems
As audio becomes an increasingly common input for AI assistants, it becomes natural to ask whether these platforms can also transcribe pre-recorded audio accurately. In this benchmark, we tested five leading generative AI models on identical English and Hungarian audio files to assess their transcription accuracy, language support, and practical
As large language models become increasingly sophisticated tools for academic writing support and web search, a critical question emerges: can the models be used also to reliably identify plagiarism? To test this capability, we embedded verbatim, unattributed passages from published academic articles into newly generated texts and asked multiple GenAI
Every time you prompt a large language model, you're witnessing the result of thousands of sequential sampling decisions—each token drawn from a probability distribution over the model's vocabulary. In standard chat interfaces, these distributions are sampled with fixed settings that users cannot adjust. But API
As AI models increasingly demonstrate coding capabilities, understanding AI-written codes' reliability and ease of use becomes essential for researchers and practitioners. In this benchmark study, we evaluated four recent models—GPT 5.2 Thinking, Opus 4.5, Gemini 3 Pro, and Grok 4.1 Expert—on two algorithm problems
Can AI detection tools reliably distinguish between human and machine-generated text? In our previous testing, we found that platforms like Originality.ai and ZeroGPT and GenAI models, frequently misclassified both AI and human text. Now, PangramLabs has gained attention with claims of near-perfect accuracy, verified by third-party organizations. In this
Log probabilities (logprobs) provide a window into how confident a language model is about its predictions. In this technical implementation, we demonstrate how to access and interpret logprobs via the OpenAI API, using a series of increasingly difficult multiplication tasks. Our experiment reveals that declining confidence scores can effectively signal
