arXiv subjects

Vanicka Arora

Publications and source records attributed to Vanicka Arora.

6 recordsLinked to original sources

arXiv2024

The Drama Machine: Simulating Character Development with LLM Agents

This paper explores use of multiple large language model (LLM) agents to simulate complex, dynamic characters in dramatic scenarios. We introduce a drama machine framework that coordinates interactions between LLM agents playing different 'Ego' and 'Superego' psychological roles. In roleplay simulations, this design allows intersubjective dialogue and intra-subjective internal monologue to develop in parallel. We apply this framework to two dramatic scenarios - an interview and a detective story - and compare character development with and without the Superego's influence. Though exploratory, results suggest this multi-agent approach can produce more nuanced, adaptive narratives that evolve over a sequence of dialogical turns. We discuss different modalities of LLM-based roleplay and character development, along with what this might mean for conceptualization of AI subjectivity. The paper concludes by considering how this approach opens possibilities for thinking of the roles of internal conflict and social performativity in AI-based simulation.

cs.CY↗

arXiv2024

Attention is All You Want: Machinic Gaze and the Anthropocene

This chapter experiments with ways computational vision interprets and synthesises representations of the Anthropocene. Text-to-image systems such as MidJourney and StableDiffusion, trained on large data sets of harvested images and captions, yield often striking compositions that serve, alternately, as banal reproduction, alien imaginary and refracted commentary on the preoccupations of Internet visual culture. While the effects of AI on visual culture may themselves be transformative or catastrophic, we are more interested here in how it has been trained to imagine shared human, technical and ecological futures. Through a series of textual prompts that marry elements of the Anthropocenic and Australian environmental vernacular, we examine how this emergent machinic gaze both looks out, through its compositions of futuristic landscapes, and looks back, towards an observing and observed human subject. In its varied assistive, surveillant and generative roles, computational vision not only mirrors human desire but articulates oblique demands of its own.

cs.CY↗

arXiv2023

(Re)framing Built Heritage through the Machinic Gaze

Built heritage has been both subject and product of a gaze that has been sustained through moments of colonial fixation on ruins and monuments, technocratic examination and representation, and fetishisation by aglobal tourist industry. We argue that the recent proliferation of machine learning and vision technologies create new scopic regimes for heritage: storing and retrieving existing images from vast digital archives, and further imparting their own distortions upon its visual representation. We introduce the term `machinic gaze' to conceptualise the reconfiguration of heritage representation via AI models. To explore how this gaze reframes heritage, we deploy an image-text-image pipeline that reads, interprets, and resynthesizes images of several UNESCO World Heritage Sites. Employing two concepts from media studies -- heteroscopia and anamorphosis -- we describe the reoriented perspective that machine vision systems introduce. We propose that the machinic gaze highlights the artifice of the human gaze and its underlying assumptions and practices that combine to form established notions of heritage.

cs.CY↗

arXiv2023

Unmaking AI Imagemaking: A Methodological Toolkit for Critical Investigation

AI image models are rapidly evolving, disrupting aesthetic production in many industries. However, understanding of their underlying archives, their logic of image reproduction, and their persistent biases remains limited. What kind of methods and approaches could open up these black boxes? In this paper, we provide three methodological approaches for investigating AI image models and apply them to Stable Diffusion as a case study. Unmaking the ecosystem analyzes the values, structures, and incentives surrounding the model's production. Unmaking the data analyzes the images and text the model draws upon, with their attendant particularities and biases. Unmaking the output analyzes the model's generative results, revealing its logics through prompting, reflection, and iteration. Each mode of inquiry highlights particular ways in which the image model captures, "understands," and recreates the world. This accessible framework supports the work of critically investigating generative AI image models and paves the way for more socially and politically attuned analyses of their impacts in the world.

cs.CY↗

arXiv2023

Truth Machines: Synthesizing Veracity in AI Language Models

As AI technologies are rolled out into healthcare, academia, human resources, law, and a multitude of other domains, they become de-facto arbiters of truth. But truth is highly contested, with many different definitions and approaches. This article discusses the struggle for truth in AI systems and the general responses to date. It then investigates the production of truth in InstructGPT, a large language model, highlighting how data harvesting, model architectures, and social feedback mechanisms weave together disparate understandings of veracity. It conceptualizes this performance as an operationalization of truth, where distinct, often conflicting claims are smoothly synthesized and confidently presented into truth-statements. We argue that these same logics and inconsistencies play out in Instruct's successor, ChatGPT, reiterating truth as a non-trivial problem. We suggest that enriching sociality and thickening "reality" are two promising vectors for enhancing the truth-evaluating capacities of future language models. We conclude, however, by stepping back to consider AI truth-telling as a social practice: what kind of "truth" do we as listeners desire?

cs.CY↗

arXiv2022

Structured Like a Language Model: Analysing AI as an Automated Subject

Drawing from the resources of psychoanalysis and critical media studies, in this paper we develop an analysis of Large Language Models (LLMs) as automated subjects. We argue the intentional fictional projection of subjectivity onto LLMs can yield an alternate frame through which AI behaviour, including its productions of bias and harm, can be analysed. First, we introduce language models, discuss their significance and risks, and outline our case for interpreting model design and outputs with support from psychoanalytic concepts. We trace a brief history of language models, culminating with the releases, in 2022, of systems that realise state-of-the-art natural language processing performance. We engage with one such system, OpenAI's InstructGPT, as a case study, detailing the layers of its construction and conducting exploratory and semi-structured interviews with chatbots. These interviews probe the model's moral imperatives to be helpful, truthful and harmless by design. The model acts, we argue, as the condensation of often competing social desires, articulated through the internet and harvested into training data, which must then be regulated and repressed. This foundational structure can however be redirected via prompting, so that the model comes to identify with, and transfer, its commitments to the immediate human subject before it. In turn, these automated productions of language can lead to the human subject projecting agency upon the model, effecting occasionally further forms of countertransference. We conclude that critical media methods and psychoanalytic theory together offer a productive frame for grasping the powerful new capacities of AI-driven language systems.

cs.CY↗