How well can today’s leading GenAI models classify real-world biodiversity data—without bespoke code or traditional machine learning pipelines? In this study, we benchmarked a range of large language models on the task of predicting penguin species from tabular ecological measurements, including both numerical and categorical variables. Using a
How far can today’s large language models go in scientific data analysis—without bespoke coding or deep learning pipelines? In this experiment, we explore the ability of DeepSeek-V3 to perform pixel-level detection of Argania trees (i.e., binary classification for each pixel) using only tabular Sentinel-2 spectral data. By
Working with real-world text data often means dealing with structures that are not yet analysis-ready. In our case, the dataset included headlines and full article texts stored separately, across two different tables. The only link between them was a shared identifier field: Body ID. Before we could begin any further
Image-based classification is increasingly used across biology, ecology, and agriculture—from identifying animal species to detecting plant diseases. One common use case is the analysis of leaf images to distinguish between healthy and diseased plants. In this post, we compare two approaches to classifying strawberry leaves as either fresh (healthy)
Working with biomedical corpora often requires programming skills, specialised formats, and time-consuming preprocessing. But what if you could transform a complex annotated dataset—like the NCBI Disease Corpus—into a structured, analysis-ready CSV using nothing more than a single, well-designed prompt? In this post, we demonstrate how a no-code, GenAI-powered
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
Generative AI has made extraordinary strides in recent years, reshaping how researchers write, code, and even analyse data. But a key question remains for academics hoping to automate more of their daily work: Can popular GenAI models like Copilot, Claude 3.7 Sonnet, Gemini 2.0 Flash, GPT-4o, Grok 3
Manus is a general-purpose AI agent designed to carry out multi-step tasks on behalf of users. It promises to understand instructions, break down complex goals, and deliver results—whether that means writing code, automating research workflows, or, in our case, retrieving public data from the web. Touted as the world’
Thematic content analysis is a key method in political text interpretation, but it typically requires human judgement to define categories and trace meaning. In this study, we explored whether Grok 3, a state-of-the-art large language model, can carry out this task autonomously—without predefined themes or external guidance. Using Martin
Can a language model accurately classify argumentative claims without any prior examples or fine-tuning? We put DeepSeek-V3 to the test on a real-world stance classification task involving 200 claims from a structured dataset. The model was asked to determine, for each claim, whether it supported (PRO) or opposed (CON) a
Argument mapping is a useful method for visualising the logical structure of reasoning, particularly in complex or multi-step arguments. In this post, we examine how Claude 3.7 Sonnet performs when prompted to identify the structure of arguments and represent them visually. The model was given five tasks, each involving
Can a generative AI model perform critical discourse analysis at a level comparable to a trained scholar? This case study puts OpenAI’s o3 model to the test by asking it to analyse Tony Blair’s 1996 “stakeholder economy” speech—a foundational text in New Labour rhetoric. The model'
