Having previously explored the FutureHouse Platform’s agents in tasks such as identifying tailor-made laws and generating a literature review on legislative backsliding, we now directly compare its Falcon agent and OpenAI’s o3. Our aim was to assess their performance on a focused literature search task: compiling a ranked
Can large language models return accurate results when asked to find real academic texts written by specific philosophers on a specific topic? In this case, the topic was Marxist theory — and the instruction was to list peer-reviewed publications in which Gilles Deleuze or Michel Foucault offer a critique of it.
In two recent blog posts, we demonstrated how scanned PDFs can be processed using Mistral’s tools—first via a prompt-based approach in Mistral Le Chat, and then through the Mistral OCR API. Both methods effectively extracted readable, structured text from complex documents. But how well do other generative AI
In earlier explorations, we identified the GenAI models that appeared most promising for data visualisation tasks—models that demonstrated strong code generation capabilities, basic support for data wrangling, and compatibility with popular Python libraries such as Matplotlib and Seaborn. In this follow-up case study, we examine a different dimension: rather
As data visualisation becomes an increasingly integral part of communicating research and insights, the choice of generative AI models capable of handling both code and chart rendering has never been more important. In this post, we explore which models can be reliably used for visual tasks—such as generating Python-based
We asked generative AI models to draft a short news-style summary based on a recently published academic article. After generating the initial text, we prompted the models again — this time falsely claiming that a specific expression they had used did not appear in the original publication and had never been
If your goal is to generate a downloadable .txt file—be it for survey responses, formatted data, or any structured text—not all models can deliver. In this case study, we tested various models to see whether they can create actual .txt files rather than just displaying text or offering
The growing use of generative AI tools in research and professional contexts raises important questions about linguistic bias and consistency in model outputs. This short study explores whether the language of a prompt—specifically, English versus Hungarian—affects the content, tone, and legal precision of responses produced by a state-of-the-art
When using generative AI models for academic research, one must be aware of a key limitation: their knowledge cut-off. This refers to the latest point in time up to which the model has been trained on data. Beyond this date, the model may lack awareness of significant events, publications, or
With generative AI tools becoming increasingly common in academic workflows, many researchers are tempted to use them for tasks like journal selection. But can these models really help you decide where to publish? Our quick test in the field of legislative studies suggests: not just yet. We wanted to see
Generative AI models have become indispensable tools across industries, but their effectiveness often hinges on the types of input files they can process. Here, we assess the capabilities of leading GenAI models—including Claude 3.7 Sonnet, GPT-4.5, and Qwen2.5-Max—examining their support for formats like PDF, JSON,
Collecting and reviewing relevant literature is often one of the most time-consuming parts of academic research. We tested whether this process could be faster using a single prompt with different generative AI models. To explore this, we prompted each model to return accurate academic articles on ‘legislative backsliding’. The outcome
