When using generative AI for structured data collection, the language of the prompt can make a real difference. In our test with Hungarian population statistics, both Claude Opus 4.1 and Sonnet 4 produced accurate outputs when prompted in Hungarian – but with an English prompt, Sonnet 4 generated rounded figures
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
These tools provide dedicated spaces for creating, refining, and managing content alongside artificial intelligence interactions, facilitating tasks from data visualisation to manuscript drafting. This guide, tailored for researchers, examines their practical applications, operational mechanisms, distinctions, version control capabilities, memory management, and availability in other models. By leveraging these interfaces, researchers
We assessed the ability of Claude 4 Sonnet and GPT-4o to classify brain MRI images as healthy or tumorous for research labelling purposes, using both the chat interface (10 images) and the API (125 images). Claude 4 Sonnet achieved perfect accuracy (10/10) in chat, but its API refused to
