Technologies
of Reading:  
From  Print  Culture to
AI-Augmented Science

Large language models belong to a long lineage of writing technologies, from the clay tokens of ancient Mesopotamia to the algorithmic tokens of today. Yet, compared to previous writing technologies, the materiality of LLMs is hard to engage. While it is possible to see the intermediate representations and activations of these systems, very little of this is legible to humans.

Interpretability research builds tools and techniques to read and make sense of the numbers inside LLMs. Interpretability researchers produce rich textual and graphical representations to understand how these models work, such as attention maps, the logit lens, and feature dashboards. For now, however, these tools are used and read largely by the computer science community.

Florilegium of Latent Operations and Representations (FLOR) brings interpretability research into dialogue with concrete and computational poetry. Its name comes from the medieval florilegium, a “gathering of flowers,” which referred to the practice of selecting excerpts and passages from authoritative texts and arranging them like a bouquet around a given topic. This practice enabled readers to reconfigure, question, and in some cases contest the texts they engaged with through the materials of manuscripts. Similarly, FLOR develops tools to collect and recompose the internal activations of LLMs to generate poetry.

Working with small open models, the project treats a model’s internals as poetic material. The aim is to open the tools of interpretability to textual scholars, poets, designers, and STS scholars, and to design margins for language models: surfaces that readers beyond the lab can write on.

For centuries, the book was a difficult technology. Producing a single manuscript required months of skilled labor, such as scribes painstakingly copying letter by letter onto prepared animal skins, grounding and mixing pigments by hand, and stitching and pressing bindings. The cost of a book could rival that of a house or a plot of land. Even after the printing press was invented, the price of paper, the weight of metal type, and the economics of distribution kept books out of most people's hands for generations. Literacy was a technical skill restricted by class, wealth, gender, and access to instruction.

What made books progressively more legible to wider audiences wasn't only the printing press or smoother paper, but the slow development of margins, interlinear gaps, glosses, and marginalia––that is, the development of spaces where readers could intervene, and comment, discuss with, and possibly contest the text.

Today's large language models are in their pre-margin era. Chat windows and explanation dashboards tell users what a model did; they rarely let users work with how it did it. And while explanation are complementary, what is needed are opportunities to interpret the material of AI.

Interpretative Interfaces is an exploration of what it would look like to make engagement with an LLM's intermediate layers as fundamental to the interaction as prompting. We present a series of prototype interface designs that treat these intermediate layers as a space for engagement. The prototypes are objects to think with; proposals for what AI interfaces could become if we designed them for interpretative engagement.

Increasingly more scientific reading begins with a prompt. Understanding Scientific Reading in the Age of LLMs is an ethnography of how this transformation is enacted in the practices of researchers. Through interviews with life scientists, neuroscientists, and other researchers in the US, Europe, and Oceania, the project traces how AI-augmented tools are reorganizing the unglamorous work of reading: how scientists discover papers, parse arguments, take notes, and construct overviews of a field.

Participants describe new forms of confidence and new forms of doubt. Certain shortcuts compress hours of work, whereas verification extends it in other ways. Some speak of LLMs as collaborators with patchy memory; some as tools that makes English-language scholarship navigable for the first time. Many describe slipping, almost imperceptibly, from reader to orchestrator, although this might be yet another shape of reading.

The project asks what kinds of reading these tools cultivate and how the labor of interpretation is being rearranged as a result. The aim is to understand how this new category of tools is reshaping what it means to know a field.