Post-creative AI

Here is a list of important terms found in the sources you have provided, including key author surnames and terms that may pique a reader’s interest.

Important Terms and Authors in “AI Urban Context combined.pdf” Excerpts

• Artificial General Intelligence (AGI): A type of AI that possesses human-like cognitive abilities and can perform any intellectual task that a human can [1].
• Apocalypse/Apocalyptic Singularity: This term, frequently appearing in discussions surrounding AI, refers to a hypothetical future point where AI surpasses human intelligence, resulting in potentially catastrophic outcomes for humanity [1].
• Attention: In the context of AI, attention refers to the mechanism by which language models focus on certain parts of the input text, similar to how humans selectively focus on information [2-9]. Multi-head attention allows models to focus on multiple aspects of the input concurrently [2, 6, 10]. The concept of an attention economy highlights how attention itself is a valuable resource in urban environments, shaping human behaviour and the design of public spaces [2, 7, 11].
• Automation/Agency: Automation in cities is discussed in relation to AI systems and their potential impact on human agency [1]. Some theorists argue that AI could lead to a decrease in human control and autonomy, while others believe AI can enhance human capabilities.
• Consciousness: The sources mention consciousness as a philosophical concept and in relation to panpsychism [1, 2, 12]. They discuss how consciousness might be understood in the context of AI systems and urban environments, and whether machines could achieve true consciousness.
• Context Window: In AI, the context window is the segment of text the model considers when processing information. This is similar to how humans use context to understand language [2, 13-17]. The urban context is discussed as a complex and multifaceted environment that influences how AI is developed and applied [2, 3, 13, 18-21].
• Conversation-centric Computation: This term refers to a computational paradigm where communication and dialogue between agents, including AI systems, are central to processing information and problem-solving [1, 22].
• Cybernetics: This field of study, which explores control and communication systems in both machines and living organisms, is mentioned in relation to semiotics and AI [23, 24].
• Design: Though not explicitly defined, design is a recurring theme in the sources, particularly in relation to urban design and the impact of AI on the built environment [4, 12, 13, 21, 25-28]. The sources imply that AI could significantly impact how we design and experience cities in the future.
• Feature Detection: This refers to the process of identifying specific elements or characteristics within data, such as images or text [13, 19]. In AI, feature detection is crucial for training models to recognise patterns and make predictions.
• Generative AI: This type of AI creates new content, such as text, images, or music, based on patterns learned from existing data [29-33].
• Large Language Models (LLMs): LLMs are a key focus in the sources. They are described as AI systems trained on vast amounts of text data that can understand and generate human-like language [2, 4, 6, 9, 13, 14, 16, 18, 34-43].
• Lexicons: In AI, lexicons are collections of words or tokens with their corresponding information, such as semantic embeddings [13, 39, 44-48]. LLMs use lexicons to look up and process language.
• Panpsychism: This philosophical view proposes that consciousness is a fundamental property of all matter, implying that even inanimate objects possess some level of awareness [1, 12, 49-52].
• Paths: In the context of semantic embeddings, paths refer to routes generated by AI systems that consider the semantic relationships between urban locations [13, 53, 54]. These paths move beyond purely spatial considerations to incorporate meanings and associations.
• Positional Encoding: This technique is used in AI models to represent the position of words within a text sequence, allowing the model to understand word order [13, 34, 41, 53, 55].
• Scripting: This concept, rooted in cognitive science, explains how we use pre-existing knowledge and patterns to understand and navigate social situations, including those found in urban environments [1, 3, 41, 56-59].
• Semantic Embeddings: These are mathematical representations of words or phrases that capture their meaning and relationships to other words [9, 13, 14, 17, 34, 36, 39, 60-68].
• Semiotics: The study of signs and symbols, particularly in relation to communication and meaning-making [13, 23, 49, 51, 69-75]. Urban semiotics focuses on how signs and symbols function in urban environments [62, 69].
• Time and Order: The sources emphasise the importance of understanding time and order in both language and urban environments. They discuss how AI models process sequences and make predictions based on temporal relationships [13, 34, 41, 42, 53, 76].
• Token Sequencing: This is the process of arranging tokens in a specific order to create meaningful sentences and paragraphs [13, 41, 77].
• Tokenisation: The process of breaking down text into individual units called tokens, which can be words, parts of words, or punctuation marks [13, 18, 19, 34, 38, 40, 45, 48, 75, 78-83]. Perceptual tokens refer to how we and AI systems identify features in visual input, such as images [18, 19, 28, 81, 84].
• Turing Test: This test assesses a machine’s ability to exhibit intelligent behaviour that is indistinguishable from human behaviour [25, 85]. It is a benchmark for measuring AI progress.
• Urban Actors: This concept explores the various agents that shape urban environments, extending agency beyond human actors to include objects, technologies, and non-human entities [86].
• Workplace Anxieties: The sources acknowledge concerns about the potential impact of AI on employment and the workforce, highlighting the need for reskilling and adaptation [1, 87].
• Abelson, R.P. [57]
• Aurigi, A. [23]
• Broadbent, G. [72]
• Chalmers, D. [49, 88]
• Coyne, R. [This author’s work is referenced extensively throughout the sources]
• Cugurullo, F. [76]
• Dreyfus, H.L. [28, 71]
• Eco, U. [72]
• Fish, S. [89]
• Foucault, M. [73]
• Gadamer, H-G [27]
• Goodman, N. [84]
• Habermas, J. [90]
• Heidegger, M. [28, 90]
• Hinton, G. [91]
• Hoel, E. [91]
• James, W. [92]
• Jencks, C. [72]
• Kipnis, J. [73]
• Kitchin, R. [93]
• Latour, B. [86]
• Leeser, T. [73]
• Lévi-Strauss, C. [94]
• Locke, J. [71]
• Malpas, J. [95]
• Minsky, M. [96]
• Mumford, L. [91]
• McLuhan, M. [97]
• Negroponte, N. [98]
• Newell, A. [97]
• Nöth, W. [23, 71]
• Ong, W.J. [99]
• Peirce, C.S. [49, 51, 100]
• Preziosi, D. [72]
• Schank, R.C. [57, 59]
• Simon, H. [97]
• Smithers, T. [101]
• Snow, C.P. [24]
• Tschumi, B. [72]
• Turing, A.M. [25, 85]
• Vaswani, A. [6, 35, 102, 103]
• Vitruvius, P. [104]
• Weizenbaum, J. [2]
• Willis, K.S. [23]
• Winograd, T. [98]
• Zuboff, S. [87]
• Zylinska, J. [25]

This list provides a starting point for understanding the key concepts and individuals shaping the discourse on AI and its relationship to language and urban contexts. The terms highlighted above represent central ideas that reappear throughout the manuscript excerpts, while the author surnames provide insight into the intellectual influences shaping the arguments presented.