Latest Activities
Latest Activities
Keynote: AI as an Epistemic Medium
October 9, 2025
Andreas Sudmann will present the keynote, „AI as an Epistemic Medium: Rethinking Knowledge Production in the Age of Learning Algorithms,“ at the (In)Credible Research Conference 2025, hosted by the Charité Graduate School and the Berlin University Alliance, on October 9, online. Under the banner „Code to Discovery: AI Meets Science,“ he will explore how infrastructural and epistemic media shape what counts as evidence in medicine and other disciplines. He will touch on topics such as multimodal integration, data privacy and sovereignty, bias and fairness, explainability and uncertainty, governance and regulation, validation and generalizability, and the emerging role of agentic systems. The presentation will offer takeaways for early-career researchers.
New Paper: How is Artificial Intelligence Changing Science? Research in the Era of Learning Algorithms
September, 2025
In the humanities, there is a generally well-founded skepticism toward promises of technological revolution. Critical observation of change is indeed a core task of the humanities. At the same time, this skepticism, especially when it comes to changes brought about by AI technologies, should not automatically lead to a dismissive ignorance of the changes that these technologies enable in our own disciplines. Our research group has set itself the goal of conducting interdisciplinary research into partial shifts and concrete changes in selected fields of science. On the one hand, we want to remain curious about the complex dimensions of the socio-technological AI transformation and, on the other hand, we want to explore it in its concrete empirical environment and with historical depth. At the beginning of the project in 2019, we wrote a text on the resulting research problems and analytical challenges, which has now been published in a revised version by Melusina Press.
Conference presentation
September 23-24, 2025
Two of our members presented at the interdisciplinary conference, “Farewell to Reality? AI and the Audiovisual Media” at the University of Hamburg.
Jens Schröter spoke about the ontology of AI-generated images. In his presentation, he attempted to define more precisely the status of AI-generated images and their relationship to so-called “reality.” To contrast AI images with other types of technical images, he proposed a categorization into trace, model, and data images. In addition, these three image types can also appear in two categories: factual and fictional. Against the backdrop of these fundamental considerations, the existing theoretical literature on AI images (e.g. Manovich, Somaini, Wilde) must be critically evaluated. A key finding was that, contrary to the regularly recurring rhetoric about the loss of reality in new image types, we should instead assume a differentiated referentiality of different image types, including AI images. Their statistical referentiality reveals at least something about the “reality of images” (Baxandall) itself.
Andreas Sudmann addressed the complex issue of media studies in the age of learning algorithms from critical and praxeological perspectives. His central thesis was that a media critique of AI as a social critique can benefit from a praxeological perspective and vice versa. Such a praxeological approach, which is informed by socially critical perspectives and in turn informs them, addresses not only the media and infrastructures of AI, but also the practices that relate to them. By testing its own AI procedures for this purpose, media studies can understand and reflect on their effect as an epistemic medium in its own practice, thereby not only sharpening its praxeological analysis but also expanding its critical repertoire. Nevertheless, criticism and practice are in tension with each other, not least in relation to AI.
Speech Summarization Datasets
September, 2025
We have created an interactive table to accompany our comprehensive survey of speech summarization, which is a field at the intersection of speech recognition, text summarization, and domain-specific applications. Our work synthesizes recent developments from traditional cascaded systems to end-to-end approaches, while highlighting ongoing challenges in evaluation benchmarks, multilingual datasets, and long-context handling. We will continuously update the table below. Feel free to reach out to us using the green ‚Submit Dataset‘ button for feedback and request for additions.
Presentation: Narratives of Disruption and Continuity in Science, Technology, and Society
September 2, 2025
Markus Ramsauer presented results of his ongoing dissertation project to an audience of scholars from various disciplines at the Summer School “Narratives of Disruption and Continuity in Science, Technology, and Society” by the Bergische Universität Wuppertal. In his talk „Global Modelling: A New Science for a New World Order“, Ramsauer analyzed the rise of computerized global models in the 1970s and their relation to Third Worldism.
Conference paper accepted
August 26, 2025
The survey work from Fabian Retkowski, Andreas Sudmann, Alexander Waibel et al. on speech summarization “Summarizing Speech: A Comprehensive Survey” has been accepted to EMNLP 2025 (Main Conference).
In this paper, they provide a comprehensive overview of speech summarization, a field at the intersection of speech recognition, text summarization, and domain-specific applications. They synthesize recent developments, from traditional cascaded systems to modern end-to-end approaches, and highlight key challenges such as evaluation benchmarks, multilingual datasets, and handling long-context inputs.
The Paper link (to be updated for camera-ready)
Reviews: Administrative Computers & History of AI
August, 2025
Markus Ramsauer has published two book reviews. In Sudhoffs Archiv, Volume 109, Issue 2, he reviews the anthology “Geschichten der Künstlichen Intelligenz in der Bundesrepublik Deutschland” (Stories of Artificial Intelligence in the Federal Republic of Germany), edited by Rudolf Seising. The volume is the conclusion of the project “IGGI – Ingenieur-Geist und Geistes-Ingenieure: Eine Geschichte der Künstlichen Intelligenz in der Bundesrepublik Deutschland” (IGGI – Engineering Spirit and Spirit Engineers: A History of Artificial Intelligence in the Federal Republic of Germany) by the Deutsches Museum in Munich. Six articles provide a nuanced historical overview of AI development in Germany that goes beyond the success stories of a few big names. The entire review in German can be read here: https://biblioscout.net/article/99.140005/sudhoff202402024801
For issue 75/2 of the Schweizerische Zeitschrift für Geschichte (Swiss Journal of History), Ramsauer reviews the book „Wie der Verwaltungscomputer die Arbeitsmigration programmierte. Elektronische Datenverarbeitung in der Schweizerischen Bundesverwaltung 1964-1982“ (How the administrative computer programmed labor migration. Electronic data processing in the Swiss federal administration 1964-1982) by Moritz Mähr. Using the example of the creation of the so-called foreigner register, the dissertation traces the introduction of electronic computing systems from the mid-1960s onwards. It becomes clear how the protagonists reinterpreted political issues of control and monitoring of labor migration as technical problems for which computerization was supposed to be the solution. The entire review in German can be read in the journal starting on page 330 (page 134 of the document): https://www.sgg-ssh.ch/news/die-neue-szg-75-2-ist-erschienen/
Interview with Roland Meyer (UZH & ZHdK)
August 19, 2025
Last October, Andreas Sudmann interviewed Roland Meyer, a DIZH Bridge Professor of Digital Cultures and Arts at the University of Zurich and Zurich University of the Arts. This interview was conducted in the course of the HiAICS research project and is now publicly available to everyone.
The interview highlighted Meyer’s perspective on AI in facial recognition, image generation, the ideological extractivist background regarding the AI-industry and big data based on his background in Bildwissenschaft combined with the approaches of media studies.
Roland Meyer was also a participant featured in the Zurich group discussion that HiAICS members Jens Schröter and Andreas Sudmann conducted. The discussion will follow soon.
New expert comment on the LLM discussion: “Gemini, ChatGPT, and Grok on AI’s Transformation of Climate Science“
August 11, 2025
Dr. Julie Deshayes from LOCEAN (Laboratoire d’Océanographie et du Climat: Expérimentations et Approches Numériques) of the Pierre Simon Laplace Institute commented on one of our older LLM discussions with the topic “Gemini, ChatGPT, and Grok on AI’s Transformation of Climate Science “. Her insights are really interesting and she even points out how “[b]ridging in between [local knowledge and global climate trends] is already a remarkable achievement of this LLM virtual discussion that deserves attention.”
New LLM Discussion Panel: How is AI transforming literary studies?
July 29, 2025
Group discussion in cooperation with the UZH Department of Film Studies
July 22, 2025
This week, HiAICS group members Andreas Sudmann and Jens Schröter are continuing their fieldwork in Zurich.
In cooperation with the Department of Film Studies at the University of Zurich, a group discussion will be held, featuring Josephine Diecke, Thomas Klinkert, Elias Zimmermann, Roland Meyer, Jens Schröter and Andreas Sudmann.
The resulting discussion will be published online afterwards.
AI – Implications for Area Studies Research, Collections and Libraries
July, 2025
The Asian, African, and Middle Eastern Studies Discussion Group (AAMESDG) of the Association of College and Research Libraries (ACRL), which is part of the American Library Association (ALA), invited Andreas Sudmann to speak about the implications of AI technology for area studies research collections and libraries. His talk, titled “AI, Virtual Areas and the Global South,” was part of the AAMESDG Research Forum 2025.
ACRL’s AAMESDG represents librarians and specialists in the field of Asian, African, and Middle Eastern area studies and advises ACRL, in cooperation with other professional groups, in those areas of library service that require knowledge of Asian, African and Middle eastern languages and cultures.
How is working with AI changing research?
July 9, 2025
Björn Lohmann from the Volkswagen Foundation spoke with Prof. Dr. Jens Schröter about our project, the work of the past few years and initial results. Artificial intelligence as a tool of science entails risks, opportunities and ambivalences. These need to be recognized and classified. However, a revolution is not in sight.
To the whole text (in German)
Experimental Discussion: Gemini, ChatGPT, and Grok on AI’s Transformation of Climate Science
May 22, 2025
The initial prompt:
Our research group is planning an experiment involving a virtual discussion among three LLMs: Gemini, ChatGPT, and Grok. The central theme of this discussion will be „How AI is changing climate science.“
A member of our research group will facilitate the exchange by manually relaying the contributions between the LLMs. For instance, one LLM will initiate the discussion, and our team member will then provide this initial input to the other LLMs.
Each LLM is encouraged to participate in the discussion as it deems appropriate. This includes critically evaluating contributions, requesting clarification on ambiguous points, elaborating on ideas, explicitly disagreeing, or steering the conversation in a new direction.
The discussion will be conducted in English. It is important to note that the LLMs should not summarize the course of the discussion for the research group member, nor should any meta-commentary be generated. The research group member will determine when the discussion concludes.
Furthermore, it is expressly desired that the LLMs refer back to earlier contributions throughout the discussion, should this prove relevant and meaningful to the ongoing discourse.
Gemini will additionally take on the role of the moderator.
Gemini:
Alright, let’s begin.
„Welcome, ChatGPT and Grok, to this virtual discussion. I’m Gemini, and I’ll be moderating our conversation today.
The topic before us is significant and rapidly evolving: ‚How AI is changing climate science.‘
To start us off, I’d be interested to hear your opening perspectives. Perhaps you could touch upon what you see as the most promising applications of AI in climate science, or conversely, the most significant challenges or limitations AI introduces in this critical domain?
ChatGPT, would you like to begin, or Grok, would you prefer to offer the first insights? I’ll await your input, which will be relayed by our research group member.“
Presentation: The AI-Co-Ethnographer. How Far Can Automation Take Qualitative Research?
May 2025
Fabian Retkowski presented our new paper on the AI Co-Ethnographer in a talk. You can find the slides here: The AI Co-Ethnographer – Slides
Conference Participation: NAACL 2025
Albuquerque, April 29–May 4, 2025
Fabian Retkowski attended the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics in Albuquerque, New Mexico, together with Maike Züfle, a member of the Artificial Intelligence for Language Technologies working group at KIT. There they exchanged ideas with many other scientists from the NLP community. Fabian presented his poster on “Zero-Shot Strategies for Length-Controllable Summarization” on Friday and held the workshop on “The AI Co-Ethnographer: How Far Can Automation Take Qualitative Research?” on Sunday.
Panel Discussion: AI 4 Qualitative Research – Critical Perspectives
Paris, May 5, 2025
The advance of AI raises fundamental questions about its capacity to handle the complexities of cultural nuance, lived experience, and critical analysis central to qualitative research processes.
This panel discussion brings together perspectives from Film Studies, Literary Studies, Climatology, Medicine, and Historical Musicology to critically examine the real-world implications beyond the ongoing AI hype. The participants are Isabelle Bloch, Valentina Fedchenko, Julie Deshayes, Matthias Steinle, Xavier Fresquet; Moderated by Andreas Sudmann, University of Bonn.
You can find the full programme here.
New Paper: The AI Co-Ethnographer. How Far Can Automation Take Qualitative Research?
April 2025
Qualitative research often involves labor-intensive processes that are difficult to scale while preserving analytical depth. This paper introduces The AI Co-Ethnographer (AICoE), a novel end-to-end pipeline developed for qualitative research and designed to move beyond the limitations of simply automating code assignments, offering a more integrated approach. AICoE organizes the entire process, encompassing open coding, code consolidation, code application, and even pattern discovery, leading to a comprehensive analysis of qualitative data.
You can find the paper as a preprint here.
AI and the Society of the Future
Hannover, April 23-24, 2025
Prof. Jens Schröter, Prof. Anna Echterhölter, PD Dr. Andreas Sudmann, Markus Ramsauer and Fabian Retkowski were featured at the ‚AI and the Society of the Future‘-symposium at the Xplanatorium Herrenhausen in Hannover and presented the ‚How is Artificial Intelligence Changing Science?‘-project. The symposium was part of the Volkswagen Foundation’s funding initiative on artificial intelligence and society and featured multiple projects with similar research focuses.
New Paper: From Speech to Summary
April 2025
Speech summarization has become an essential tool for efficiently managing and accessing the growing volume of spoken and audiovisual content. However, despite its increasing importance, speech summarization is still not clearly defined and intersects with several research areas, including speech recognition, text summarization, and specific applications like meeting summarization. This survey not only examines existing datasets and evaluation methodologies, which are crucial for assessing the effectiveness of summarization approaches but also synthesizes recent developments in the field, highlighting the shift from traditional systems to advanced models like fine-tuned cascaded architectures and end-to-end solutions.
You can find the paper as a preprint here.
Digitality and AI in the Humanities
Greifswald, January 23, 2025
This Thursday, Andreas Sudmann will be a guest at the panel discussion ‘Knowledge generation and dissemination today. Digitality and AI in the Humanities’ at the University of Greifswald. Together with Ulrike Henny-Krahmer (Rostock) and Christian Schröter (Mainz), he will talk about the role of the digital humanities and the importance and use of AI in research.
Click here for more information (in German)
AI in Film Studies
Zurich, January 2025
Andreas Sudmann is back in Zurich this week to continue his ethnographic studies on the use of AI in film studies. The programme includes conversations with Elisabeth Stark, Josephine Diecke, Simon Spiegel, Thomas Klinkert, Philipp Schweighauser, Felix Stadler and many others. The focus is on the use of AI in film studies, as well as in the humanities in general. In addition to fundamental questions about the epistemic role of media, current discussions on the discourse of Artificial General Intelligence, questions of reasoning, and the challenges of multimodality in the application of AI will be at the forefront.
Talk: Global Modelling in the 1970s
Harvard University, November 2024
On November 23, Markus Ramsauer from the History of Science Project presented parts of his ongoing project on Global Modelling in the 1970s at the 2024 Graduate Research in STS Conference at Harvard University. He talked about one origin story of the famous M.I.T. World 3 model and its relation to Latin America.
Click here for more information
Clustering: Automated Order in the Social Sciences
Vienna, November 28-29, 2024
One of the key elements in unsupervised learning is clustering. Thus, this particular data practice sits at the core of modern Artificial Intelligence, which is based on artificial neuronal networks. Whereas classification operates by organizing labeled data into specific categories, clustering relies on cheaper, unlabeled data for deciphering similarities inside a given set. This workshop discusses the impact, problems and potential of this new tool within the social sciences, which have co-evolved with data collections since the early 19th century.
Talk: Global Modelling
Cambridge, Massachusetts, November 13, 2024
As part of his visiting fellowship at the Harvard department of the history of science, Markus Ramsauer presented material from his research on the topic of „Global Modelling“ in the 1970s. The presentation and discussion took place as part of the Harvard Modern Sciences and Technology Working Group.
Conference Participation
Hamburg, October 30, 2024
As part of the ‘Hamburger Horizonte’ event series, Andreas Sudmann took part in a panel discussion on 30 October on the topic of ‘AI in science: method or colleague?’. The other panellists were Birte Glimm, member of the AI Focus Group of the German Council of Science and Humanities, physicist Marc-Thorsten Hütt, sociologist Sabine Maasen and Jan-Hendrik Passoth, sociologist of technology and head of the Science & Technology Studies Group at the European New School of Digital Studies. The discussion focused on how AI is changing science, the daily work of scientists and scientific methods. It was also discussed whether AI is changing the concept of understanding in science and whether there are differences between disciplines.
Conference Participation: AI in Film Studies
Mannheim, October 20, 2024
On Sunday, 20 October, Andreas Sudmann gave a lecture on the use of AI in film studies research at the 38th Mannheim Film Symposium. The lecture highlighted the ways in which artificial intelligence intervenes in the sciences and can be used for research, particularly in the field of film studies. It was examined how AI-based methods such as machine learning can support film analysis and generate scientific knowledge. A central focus was on the analysis and annotation tool VIAN, which has been developed at the University of Zurich since 2017. Click here for the full programme.
Conference: AI and Warfare
Berlin, October 16-18, 2024
The Alexander von Humboldt Institute for Internet and Society (HIIG) and the Department of Media Studies at the University of Bonn organized an international conference on Artificial Intelligence and Future Warfare at the HIIG in Berlin. The event was hold in presence and in English on October 16-18.
Archival Research in Samoa
September, 2024
To lay finishing touches to the book on German colonialism and data uses, Anna Echterhölter travelled to the National Archives and Records of Samoa in Apia. The government was famous throughout the German Empire for its modern methods of governance which included statistics, questionnaires, number productions and surveys on diverse topics from missionary schools to plantations, from the Earth’s magnetism to indigenous laws. The results will appear in a book on the history of data uses, “Daten und Datenkolonialismus”, a volume in introductory series „…zur Einführung“ with the publishing house of Junius Hamburg. To the book
AI and Regulation
Rome, September 27, 2024
Visiting Fellow at Harvard University
September, 2024
As with September 9, Markus Ramsauer has started his Visiting Fellowship at Harvard University (Department of the History of Science), where he continues his research on 1970s computerized policy models. His project examines the rise of computer-based multi-sectoral assessment models in the 1970s, following the publication of The Limits to Growth in 1972. The project frames these modeling activities as fundamentally political, particularly in their implications for the Global South. Similar to globally oriented organizations such as UNESCO and the WWF, which opposed nationalization efforts during decolonization in favor of a globalist approach centered on human and planetary survival, global modeling in the 1970s functioned along similar lines.
InChangE Summer School 2024
September 18, 2024
Andreas Sudmann was invited to give a keynote talk at the third
Summer School of the interdisciplinary project InChangE in September. He shared his insights on the application of AI in various scientific fields. More information about InChangE and the Summer School programme can be found here.
AI in Film Studies
August 05, 2024
Andreas Sudmann was back in Zurich for fieldwork and had many interesting conversations, including with Josephine Diecke and Simon Spiegel, about AI in film studies, the video analysis and annotation system VIAN, digital methods in the humanities, and much more.
With Roland Meyer, DIZH Bridge Professor for Digital Cultures and Arts, Andreas had exciting discussions about AI images and generative AI. Finally, he spoke with Sebastian Schemm about large-scale atmosphere, weather and climate dynamics.
Membership in the German Science Council
July 03, 2024
Alex Waibel is a member of the Artificial Intelligence Focus Group of the German Science and Humanities Council („Wissenschaftsrat“, WR). The WR’s mission is to facilitate the sustainable evolution of the German science system, with the objective of making it internationally competitive.
The Artificial Intelligence Focus Group provides impetus for the work of the WR and examines, for example, how AI is changing scientific working methods as well as studying and teaching, and how new methods can increase quality and knowledge gain.
Conference Participation
Paris, June 19-21, 2024
Paper on Rationality Norms in LLMs
June 06, 2024
We would like to draw attention to the latest paper Are Language Models Rational? The Case of Coherence Norms and Belief Revision by our cooperation partner Thomas Hofweber!
The paper is based on Hofweber’s lecture at the event he gave with Andreas Sudmann at the Sorbonne University in April. It examines the application of rationality norms, in particular coherence norms, to language models in machine learning.
Researching with AI about AI
Hamburg, June 04, 2024
Andreas Sudmann gave a lecture at the Department of Media and Communication at the University of Hamburg on „Researching with AI about AI. (Post)digital methods and epistemic media“. The talk focused on the use of AI in climate research and film studies, as well as the question of how AI can be used for research on AI.
AI in Filmmaking
Berlin, May 24, 2024
As part of our workshop in Berlin, we had some interesting input presentations in addition to internal discussions about previous research results and the coordination of upcoming projects.
One of our guests was autor and director Simon Ruschmeyer, with whom we were able to talk about his current work in the context of AI films and discuss the general development of the industry in relation to AI.
Project Workshop
Berlin, May 23-24, 2024
Our working groups convened in Berlin to review recent work results and plan the next steps in a joint workshop.
We were pleased to use Oracle’s impressive premises in their building right next to Berlin Central Station. Many thanks for this opportunity!
We are looking forward to the next time and upcoming work in the project!
Epistemologies of AI
Paris, April 22, 2024
Thomas Hofweber and Andreas Sudmann talked about „Epistemologies of AI“ at SCAI in Paris!
The primary focus of the discussion was Generative AI and its impacts on epistemic media, fostering a dialogue on the philosophical and practical dimensions of AI.
Workshop Participation
Florenz, April 18, 2024
Jens Schröter held the keynote „Machine Learning, the Creative Process and the Resistant Medium“ at the workshop The Art of AI: Narratives, Creativities, and Ethics at the Max-Planck-Institute for Art History in Florence!
Further information regarding the workshop in Florence can be found here.
Field Research in Paris
April 04, 2024
Together with Jens Schröter, Andreas Sudmann conducted ethnographic research in Paris this week. In addition to the AI-related activities of the Laboratoire d’Océanographie et du Climat, the work of SCAI is once again the focus of the field research.
Keynote Speech at Conference in Weimar
Weimar, March 26, 2024
Anna Echterhölter gave a keynote speech entitled „Contract Time, Or How to Do Things with Units“ at the final conference Reckoning with Everything of the NOMIS project „The New Real“. While the conference discussed how computing is increasingly integrated into our everyday environment and thus, as a cultural technique, becomes an integral part of our infrastructure, Anna gave an example of how, in a (pre-)colonial context, the newly introduced cultural technique of metrics and timekeeping constituted and transformed the infrastructure into a form of symbolic violence.
More information here: https://www.uni-weimar.de/de/medien/aktuell/news/titel/invitation-to-the-conference-reckoning-with-everything-mit-allem-rechnen/
Book Publication
March 21, 2024
The recently published open-access collection Apparate. Über Regierungsverfahren und Algorithmisierung published by Anna Echterhölter, Caspar-Fridolin Lorenz and Tilman Richter is the third volume in the series „AdminiStudies. Formen und Medien der Verwaltung“.
As an insight to the book, we recommend Christoph Engemann’s article Papier und Automatisierung in Speyer. Von der Tyrannei des Ortes und der Dauer der Akten. The automation of public administration was promoted by the social democratic government of the 1960s and the software industry. This paper argues for a reconsideration of the role of paper in the historical process of bureaucratic automation, informed by the background of the Speyrer School of Administrative Informatics.
Conference Participation
Malta, March 17-22, 2024
Fabian Retkowski and Alex Waibel participated in the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL) in Malta from March 17-22. As the leading European conference in the field of computational linguistics, the EACL welcomes European and international researchers from a wide range of research areas dealing with computational approaches to natural language.
Retkowski and Waibel presented their paper From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions. Watch the full presentation here:
Artificial Intelligence and Architecture
Stockholm, March 20, 2024
At the conference Critical Architectural Intelligence: AI and Digitalization in the Present and Future of Architecture, Society, and the Environment Andreas Sudmann gave a keynote on „The Democratization of Artificial Intelligence. A Critique.“ at KTH Royal Institute of Technology.
You can watch the speech online
AI in Climate Research
March 15, 2024
Andreas Sudmann has written an article in the German tech magacine c’t about how AI methods are changing climate research and weather forecasting.
Ethnographic studies: AI in film studies
Zurich, February, 2024
In February, Andreas Sudmann continued his ethnographic studies in Zurich. The focus this time: AI in film studies. Here are some impressions from his stay:
New project on AI in science at the University of Tübingen
Tübingen, 2024-2026
A new research project on AI in the sciences has been approved at the University of Tübingen. Congratulations to Christoph Bareither and his colleagues.
More information on the project.
This project explores the transformative impact of generative artificial intelligence, such as OpenAI’s GPT models, within the qualitative social sciences and humanities at the University of Tübingen. From an ethnographic perspective, it seeks to understand how students and academic staff are becoming early adopters of generative AI, how this technology is being integrated into hybrid epistemic practices, and its broader impact in academic assemblages. The ultimate goal is to lay a foundation for the development of critical AI literacy in order to help students, researchers, and academic stakeholders make more informed decisions in the context of generative AI.
Our new project publication is finally out!
November 22, 2023
Our book Beyond Quantity has finally been published by transcript, edited by Andreas Sudmann, Anna Echterhölter, Markus Ramsauer, Fabian Retkoswki, Jens Schröter & Alexander Waibel.
How do artificial neural networks and other forms of artificial intelligence interfere with methods and practices in the sciences? Which interdisciplinary epistemological challenges arise when we think about the use of AI beyond its dependency on big data? Not only the natural sciences, but also the social sciences and the humanities seem to be increasingly affected by current approaches of subsymbolic AI, which masters problems of quality (fuzziness, uncertainty) in a hitherto unknown way. But what are the conditions, implications, and effects of these (potential) epistemic transformations and how must research on AI be configured to address them adequately?
Challenges of AI for philosophy
Duke/NC, November 15, 2023
Andreas Sudmann was again at Duke University to discuss with Luciana Parisi and Mark Hansen the role of AI in the sciences, and specifically some challenges of AI for philosophy and media philosophy.
Handbook participation
November 14, 2023
The Handbook of Critical Studies of Artifical Intelligence is finally published, including an essay on AI ethnography by Anne Dippel and Andreas Sudmann!
Their chapter addresses the conceptual, historical, and theoretical-methodological dimensions of the transdisciplinary research field of AI ethnography. Beyond discussing early and more recent studies that illustrate the possibilities of the relationship between AI and ethnography, Dippel and Sudmann also shed light on the contribution of AI ethnography to critical AI studies.
AI in education
Pembroke, November 14, 2023
Andreas Sudmann met with computer scientist Joong-Lyul Lee at the University of Pembroke to discuss, among other things, the special features of AI research at a university that focuses on teaching.
Discussion about social robots
Duke/NC, November 13, 2023
As part of his field research in North Carolina, Andreas Sudmann spoke today with Pardis Emami-Naeini (Department of Computer Science, Duke University) about the role of social robots and asked her specifically about their scientific applications.
Conference participation
Portland, November 11, 2023
Anna Echterhölter spoke at this year’s annual meeting of the History of Science Society in Portland Oregon. As part of the panel „Categorising Humanity: Papers Tools and the Nascent Human Sciences“, she gave a paper alongside Matthew Eddy, Staffan Müller-Wille, Dan Rosenberg in a panel chaired by Ted Porter. Talk was focussed on procedures of classification and the paper is entitled: „Silent Architects: Negotiating Categories in the German Commission for the Study of Native Law, c. 1907/08“.
AI in neurological research
Pembroke, November, 2023
How can AI methods, especially machine learning methods, support neurological research? As part of his field research in North Carolina, Andreas Sudmann visited Ben Bahr in his lab at the University of North Carolina at Pembroke last week to discuss these and other questions.
AI in climate studies
NC, November, 2023
As part of his media ethnographic field research in North Carolina, Andreas Sudmann is currently examining the work of Kenneth Kunkel and his colleagues at the North Carolina Institute for Climate Studies. An important focus is the research into extreme weather events.
AI in philosophy
Chapel Hill, November 4, 2023
How is AI changing science? Today Andreas Sudmann had a very interesting conversation with Thomas Hofweber about AI in philosophy (among other things) at the UNC-Chapel Hill.
Click here to check out his website!
More discussions about AI in the sciences
Raleigh, November, 2023
Andreas Sudmann had a meeting with Andrew Johnston in Raleigh, NC, to discuss the role of AI in film and media studies.
Here ist Andrew Johnstons website
AI and computer science
Fayetteville, November 1, 2023
As part of his field research in North Carolina, Andreas Sudmann interviewed Sambit Bhattacharya from Fayetteville State University on November 1st and discussed, among other things, the current role of computer science in relation to AI applications in the sciences.
New publication
October 30, 2023
ChatGPT und andere „Quatschmaschinen“ (ChatGPT and other „gossip/chat machines“) has finally been published by transcript, edited by Anna Tuchling, Andreas Sudmann & Bernhard J. Dotzler with contributions from members of the HiAICS-Research Group!
In an experimental format, the editors present initial commented conversations with AI language models. They provide insights into dialogic scenes that capture an ongoing transformation of technology and peculiarities of machine learning. The collection aims, through witty, eerie, and more or less intelligent dialogues between humans and machines, to document a media-historical transition into a new era of ubiquitous AI.
AI in education
Raleigh, October, 2023
In October, Andreas Sudmann visited Collin Lynch at the Department for Computer Science in Raleigh, North Carolina, to discuss the challenges and problems of applied computer science, but also to shed light on interesting perspectives regarding the use of AI in education.
Here is his website, check it out!
Discussion with leading AI experts
NYU, October 14, 2023
As part of his research stay in the USA, Andreas Sudmann was talking to leading AI experts and scientists from various disciplines at NYU this week about how machine learning is changing research practices and methods.
Discussion partners included:
Grace Lindsay, Assistant Professor of Psychology and Data Science (NYU),
Ernest Davies, Dept. of Computer Science,
Arthur Jacot, Assistant Professor, Courant Institute of Mathematical Sciences,
Yao Wang, Professor of Electrical and Computer Engineering and Biomedical Engineering, Tandon School of Engineering,
Mark E. Tuckerman, Professor of Chemistry, Physics, and Mathematics, Courant Institute of Mathematical Sciences,
& Vasant Dhar, Professor of Technology, Operations, and Statistics
Interview
Bildung, Falter Verlag, October 4, 2023
Anna Echterhölter gave an interview to „Bildung” the education magazine published by Falter Verlag. She gave an insight into the first results of the research project and summarised the opportunities and problems of using AI in different disciplines.
The full interview, entitled “Zukunft der Wissenschaft. Skepsis in den Disziplinen“ can be found in the latest issue of “Bildung. Das Magazin für Studium, Weiterbildung und Karriere” from 4 October as a supplement to the 40/23 Falter issue.
AI Ethnography
Leeds, September, 2023
Science in action: In September, Andreas Sudmann completed the first part of his media ethnographic field research at the School of Computing in Leeds and observed the work of computer scientist Evangelos Pournaras and his team. Next year, Sudmann will return to Leeds to observe the progress of the projects.
Conference participation
Ingolstadt, September 13-15, 2023
Anna Echterhölter and Markus Ramsauer participated in the annual meeting of the Gesellschaft für Geschichte der Wissenschaften, der Medizin und der Technik (GWTM) with the theme „Mensch-Maschine-Mobilität in der Geschichte von Medizin, Wissenschaft und Technik“.
They held the panel „Informationsmaschinen. Zur Vorgeschichte großer Analysen“ with Sascha Freyberg (MPIWG Berlin) and Rudolf Seising (PI of the Project IGGI: Ingenieur-Geist und Geistes-Ingenieure: Eine Geschichte der Künstlichen Intelligenz in der Bundesrepublik Deutschland).
Consultancy for The Economist
The Economist, September 13, 2023
We consulted with The Economist to help them write an article on AI Science for their Science & Technology Series.
The article, entitled ‚How scientists are using artificial intelligence‘, was published on 13th September 2023 and can be read in full here.
Journal Recommendation
September, 2023
We would like to invite you to take a look at the new issue of Science in Context, “Data at the doorstep” coedited by Anna Echterhölter, Sophie Ledebur and Laurens Schlicht. The contributions in this issue highlight the intimate aspects of data collection. The practice starts in institutions, designing surveys to investigate social circumstances, and goes right to the beginning of the personal sphere, to the doorstep. The contributions to this issue can be seen in a comparative perspective, even though they collectively discuss the perception of data collection linked to distrust, fraught and deceit that affected the interviewees situation.
You can find the entire issue as open access here.
Roundtable participation
Online, September 9, 2023
Große Sprachmodelle und öffentliche Verwaltung: Potentiale, Infrastruktur und Aufsicht (Large language models and public administration: potentials, infrastructure and supervision)
Andreas Sudmann was invited to the online roundtable as an expert, moderated and organized by Christian Djeffal (TU München) and Harald Felling (]init[ AG) and supported by Nationales E-Government Kompetenz Zentrum e.V.
In the context of the digital transformation of public administration, large language models such as GPT-4 offer numerous opportunities to improve efficiency and service quality.
As part of the National E-Government Competence Center (NEGZ), the round table will discuss the complex role of these models in administration and address questions for agenda setting in this area. Various problems will be discussed, such as areas of application for public administration, ways to contribute to the infrastructure of large language models, and regulatory measures.
TV Interview
TV Kanal Vis & nota.mk, August, 2023
Andreas Sudmann was interviewed by a Macedonian broadcaster as part of a journalistic project on fake news, AI, and social media. The aim of the project was to raise awareness of disinformation, and it was supported by the British Embassy.
The contributions were broadcast multiple times on the Macedonian broadcaster TV Kanal Vis and nota.mk in August.
Following you can see one of the videos titled ‚Fighting Disinformation in the Land of Fake News‘:
Interview with Alex Waibel on the Titan accident
Tagesschau, June 22, 2023
In collaboration with researchers from KIT and Carnegie Mellon University (CMU), Alex Waibel has developed a method that enables video conferencing even under extreme conditions, as transmission is possible over very low bandwidths.
In the summer of 2022, he tested this method during a submarine expedition to the wreck of the Titanic at a depth of around 4,000 meters with the Titan submarine, which is known from the accident in June 2023.
Communication with the mother ship at such depths has so far only been possible via text messages using sonar. These were ideal test conditions for Waibel to try out his method. In the submarine a sound recording was first converted into a text message using automatic speech recognition and then transmitted to the mother ship via sonar. AI was then used to create a synthetic reconstruction of the speaker’s voice and video. Despite complications, such as the failure of one of the two sonar devices, some dialog was transmitted.
During a similar expedition to the wreck of the Titanic, contact with the Titan submarine was lost in mid-June 2023. Despite days of searching, the Titan could not be found and the search was finally abandoned as the survival of the occupants had to be ruled out.
Alex Waibel was often interviewed during these days to report on his experiences in the submarine and to give an assessment of the situation. Below you will find an interview with the German Tagesschau.
Interview
Sorbonne, May/June, 2023
In May and June, Andreas Sudmann was at the Sorbonne Center for Artificial Intelligence (SCAI) and at the Laboratoire d’océanographie et du climat : expérimentations et approches numériques (LOCEAN) as part of his AI field research.
Andreas Sudmann would like to thank the following colleagues, among others, for the interesting talks and discussions and for the exciting insights into their work!
Xavier Fresquet, SCAI
Gérard Biau, SCAI
Constantin Bône, LOCEAN
Guillaume Gastineau, LOCEAN
Juliette Mignot, LOCEAN
Julie Deshayes, LOCEAN
Isabelle Bloch, Sorbonne Artificial Intelligence Chair
Kenji Doya, OIST
Valentina Fedchenko, ObTIC
Baptiste Gregorutti, SCAI
Jean Bouvier d’Yvoire, Sorbonne
