Hands-On Prompt-Tutorials for Using GenAI in Research and Education
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
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
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
Claude Projects recently introduced a Retrieval-Augmented Generation (RAG) feature that extends its capabilities beyond the standard context window. Unlike traditional approaches that require custom vector databases and API integration, Claude's implementation offers a streamlined, no-code solution for handling large knowledge bases directly within the Projects interface. In this
Tool use (also called function calling) is one of the most powerful capabilities available in modern language models. It allows models to extend beyond text generation by interacting with external systems, databases, or custom logic—making AI agents capable of real-world tasks like checking weather, querying APIs, or running calculations.
In this post we put Notebook LM’s new literature review feature to the test. The model was given six pre-selected sources on a single topic and asked to produce a structured review. The results were not bad at all: the output drew appropriately on the provided references and offered
Prezi’s new AI tool promises to transform documents into ready-made presentations. Our tests show that while the tool produces visually appealing slides, the generated content often drifts away from the uploaded source material. Using sustainability reports from Audi and the Hungarian National Bank, as well as an academic article,
In a previous blog post, we focused on input file handling in leading GenAI interfaces, mapping out which formats could be uploaded and processed reliably, and where the main limitations were. This time, we turn to the other side of the equation—output generation—with a concrete test case: producing
In a previous blog, we examined the file handling capabilities of leading GenAI interfaces. That analysis detailed which formats they could process reliably and where they encountered difficulties—particularly with structured data and technical file types. Since then, the landscape has shifted. While downloadable file generation still faces notable constraints,
