We present a web-based environment that connects annotation, abstraction, and argumentation during the interpretation of text. As a visual interface for scholarly reading and writing, Textarium combines human analysis with lightweight computational processing to bridge close and distant reading practices. Readers can highlight text, group keywords into concepts, and embed these observations as anchors in essays. The interface renders these interpretive actions as parameterized visualization states. Through a speculative design process of co-creative and iterative prototyping, we developed a reading-writing approach that makes interpretive processes transparent and shareable within digital narratives.

September/October 2025

It can be said the neural networks (specially in their sophisticated forms) account for such abstract recoding, but this is not fully satisfactory, because there is just one network in the model; a different approach is to use layers of neural networks, where the higher level takes as inputs the patterns of the lower, sensory, layers (Sun, 2006), but up to now this is done " by hand " . Still another approach, of Vygotskian inspiration, views in the use of public symbols the key to understand cognitive, abstract recoding (Gomila, 2012), but the application of this approach within artificial cognitive systems is just beginning. Flexible use of knowledge Extracting world regularities and contingencies would be useless unless such knowledge can guide future action in real - time in an uncertain environment. This may require in the end, as anticipated above, behavioral unpredictability, which is a property than runs contrary to the technical requirements of robustness and reliability for artificial systems (to guarantee safety, as the principal engineer ' s command). The critical issue for flexibility is related to how the knowledge is " stored " (see previous section), and therefore, how it is accessed. The major roadblock to carry this out - regardless of approach - is again combinatorial explosion, whether at the level of propositional representations, as in classical AI, or at the level of degrees of freedom for the control of actuators. But it is also a problem to " judge ", in a given situation, which one is the best one to categorize it, given what the system knows.

Safety has become the central value around which dominant AI governance efforts are being shaped. Recently, this culminated in the publication of the International AI Safety Report, written by 96 experts of which 30 nominated by the Organisation for Economic Co-operation and Development (OECD), the European Union (EU), and the United Nations (UN). The report focuses on the safety risks of general-purpose AI and available technical mitigation approaches. In this response, informed by a system safety perspective, I refl ect on the key conclusions of the report, identifying fundamental issues in the currently dominant technical framing of AI safety and how this frustrates meaningful discourse and policy efforts to address safety comprehensively. The system safety discipline has dealt with the safety risks of software-based systems for many decades, and understands safety risks in AI systems as sociotechnical and requiring consideration of technical and non-technical factors and their interactions. The International AI Safety report does identify the need for system safety approaches. Lessons, concepts and methods from system safety indeed provide an important blueprint for overcoming current shortcomings in technical approaches by integrating rather than adding on non-technical factors and interventions. I conclude with why building a system safety discipline can help us overcome limitations in the European AI Act, as well as how the discipline can help shape sustainable investments into Public Interest AI.

A central goal of linguistic theory is to find a precise characterization of the notion "possible human language", in the form of a computational device that is capable of describing all and only the languages that can be acquired by a typically developing human child. The success of recent large language models (LLMs) in NLP applications arguably raises the possibility that LLMs might be computational devices that meet this goal. This would only be the case if, in addition to succeeding in learning human languages, LLMs struggle to learn "impossible" human languages. Kallini et al. (2024; "Mission: Impossible Language Models", Proc. ACL) conducted experiments aiming to test this by training GPT-2 on a variety of synthetic languages, and found that it learns some more successfully than others. They present these asymmetries as support for the idea that LLMs' inductive biases align with what is regarded as "possible" for human languages, but the most significant comparison has a confound that makes this conclusion unwarranted. In this paper I explain the confound and suggest some ways forward towards constructing a comparison that appropriately tests the underlying issue.

This paper presents Coralai, a framework for exploring diverse ecosystems of Neural Cellular Automata (NCA). Organisms in Coralai utilize modular, GPU-accelerated Taichi kernels to interact, enact environmental changes, and evolve through local survival, merging, and mutation operations implemented with HyperNEAT and PyTorch. We provide an exploratory experiment implementing physics inspired by slime mold behavior showcasing the emergence of competition between sessile and mobile organisms, cycles of resource depletion and recovery, and symbiosis between diverse organisms. We conclude by outlining future work to discover simulation parameters through measures of multi-scale complexity and diversity. Code for Coralai is available at https: //github.com/aidanbx/coralai,

The article is an attempt to contribute to explorations of a common origin for language and planned-collaborative action. It gives `semantics of change' the central stage in the synthesis, from its history and recordkeeping to its development, its syntax, delivery and reception, including substratal aspects. It is suggested that to arrive at a common core, linguistic semantics must be understood as studying through syntax mobile agent's representing, tracking and coping with change and no change. Semantics of actions can be conceived the same way, but through plans instead of syntax. The key point is the following: Sequencing itself, of words and action sequences, brings in more structural interpretation to the sequence than which is immediately evident from the sequents themselves. Mobile sequencers can be understood as subjects structuring reporting, understanding and keeping track of change and no change. The idea invites rethinking of the notion of category, both in language and in planning. Understanding understanding change by mobile agents is suggested to be about human extended practice, not extended-human practice. That's why linguistics is as important as computer science in the synthesis. It must rely on representational history of acts, thoughts and expressions, personal and public, crosscutting overtness and covertness of these phenomena. It has implication for anthropology in the extended practice, which is covered briefly.

We investigate the representational power of sum-product networks (computation networks analogous to neural networks, but whose individual units compute either products or weighted sums), through a theoretical analysis that compares deep (multiple hidden layers) vs. shallow (one hidden layer) architectures. We prove there exist families of functions that can be represented much more efficiently with a deep network than with a shallow one, i.e. with substantially fewer hidden units. Such results were not available until now, and contribute to motivate recent research involving learning of deep sum-product networks, and more generally motivate research in Deep Learning.

We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples n for all tasks. For GP covariances that are the product of an input-dependent covariance function and a free-form intertask covariance matrix, we show that accurate approximations for the learning curve can be obtained for an arbitrary number of tasks T. We use these to study the asymptotic learning behaviour for large n. Surprisingly, multi-task learning can be asymptotically essentially useless, in the sense that examples from other tasks help only when the degree of inter-task correlation, ρ, is near its maximal value ρ = 1. This effect is most extreme for learning of smooth target functions as described by e.g.

Warped Gaussian processes (WGP) [1] model output observations in regression tasks as a parametric nonlinear transformation of a Gaussian process (GP). The use of this nonlinear transformation, which is included as part of the probabilistic model, was shown to enhance performance by providing a better prior model on several data sets. In order to learn its parameters, maximum likelihood was used. In this work we show that it is possible to use a non-parametric nonlinear transformation in WGP and variationally integrate it out. The resulting Bayesian WGP is then able to work in scenarios in which the maximum likelihood WGP failed: Low data regime, data with censored values, classification, etc. We demonstrate the superior performance of Bayesian warped GPs on several real data sets.