In this post we present a comparative test of several generative AI models, focusing on their ability to retrieve official sports statistics. The task involved collecting NBA game data through a single prompt, with the expectation that the models would accurately locate, extract, and structure the requested information. While the
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 our earlier blog post, Harnessing GenAI for Searching Literature: Current Limitations and Practical Considerations, we examined the reliability of generative AI models for scholarly literature searching. To assess whether the newest releases represent any improvement, we tested them on the same narrowly defined academic topic. The results indicate modest
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,
We tested the new OpenAI Agent to assess its usefulness in academic research tasks, comparing it directly with Manus.ai and Perplexity’s research mode. Our aim was to evaluate how effectively each tool finds relevant scholarly and policy sources, navigates restricted websites (including captchas and Cloudflare protections), and allows
Academia.edu has recently introduced an AI-based Reviewer tool, positioned as a solution for generating structured feedback on academic manuscripts. While the concept is promising, our evaluation revealed a number of significant limitations. We encountered recurring technical issues during both file uploads and Google Docs integration, often requiring multiple attempts
High-quality feedback is essential for researchers aiming to improve their work and navigate the peer review process more effectively. Ideally, such feedback would be available before formal submission—allowing authors to identify the strengths and weaknesses of their research early on. This is precisely the promise of OpenReviewer, an automated
In this post, we examine the performance of Manus’s newly updated slide generation tool when applied to a peer-reviewed scientific article. The developers claim recent improvements focused on enhancing the tool’s ability to support academic communication. To test these capabilities, we selected a published study in political science
As AI-assisted tools become increasingly embedded in academic publishing, most major journal platforms now offer automated systems that claim to recommend suitable outlets based on a manuscript’s abstract. But how well do these tools perform in practice? To explore this, we tested five journal finder platforms — four developed by
Following our previous evaluations of the FutureHouse Platform’s research agents this post turns to Owl, the platform’s tool for precedent and concept detection in academic literature. Owl is intended to help researchers determine whether a given concept has already been defined, thereby streamlining theoretical groundwork and avoiding redundant
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
