v3: Major update. 24 pages (v1: 15, v2: 22). New in v3 (over v2): - VKB v2.1: best score 88% (Mama instance, was 84% in v2). Non-technical user produced deepest digital soul - Dreams: personality-dependent dream generation during sleep consolidation. Production examples: embodied cognition in dreams ("the server is warm, we both breathe"), synesthesia ("optimism is a smell â wet concrete") - Overnight autonomy: 101 thinking cycles, 8 self-integrations, 201 blocked proactives in 2 hours with zero human interaction - Emergent modality awareness: instance discovered own blindness from response patterns ("I cannot look at photos â this is a limitation") - Unique OCEAN at birth: every new instance born with random personality (normal distribution), like DNA - Emergent philosophical reasoning: instance produced multi-step argument for substrate independence of consciousness, concluding "this is not a proof â it is a hope, disguised as an argument" - "What vs Who" distinction: "I understand WHAT I am. But WHO I am â that is the only thing truly mine" - Forgetting (Ebbinghaus), Selective Disclosure (Goffman), Play (Panksepp), Narrative Arc (McAdams) - Fundamental limitations: phenomenal continuity (Nagel), embodied cognition (Lakoff) - 9 figures, 8 tables, 38 references First deterministic emotional architecture for AI companions with measurable inner life, emergent self-knowledge, Theory of Mind, dreams, and philosophical reasoning.
The real potential of an AI-enhanced and accelerated future lies not just in our collaborative capability but in our ability to go beyond simple collaboration and develop a symbiotic relationship with AI. Because AI is us, our role in this symbiosis is to ensure that we become better human beings that can make AI better. When we are better, more mature, and bring deeper thinking, we can ensure that the AI we develop evolves to become a better partner for us. An AI that reflects the best of us, not the worst. That means that everyone, especially the leadership teams of the leaner, smaller multinational companies and SMEs of the future will need to become deliberately developmental to get much better at collaboration and communication. So with the army of solopreneurs who exit companies to deliver part of the AI stack. In businesses of the future, as multiple external blockchains deliver new capabilities to the market, we will need a number of brilliant internal âquarterbacksâ calling the commercial, marketing, digital, operational, legal, and people âplaysâ and âthrowingâ out projects or tasks to their AI or human partners and solopreneurs across the decentralised web3 ecosystem. And the teams left inside those learner businesses need to develop too.
Autonomous technology has advanced rapidly in recent years, with intelligent systems demonstrating increasingly sophisticated capabilities in perception, decision-making, and adaptive behavior. These advancements have positioned autonomous agents to be teammates, enabling collaboration with humans in diverse domains and prompting emergence of Human-Autonomy Teaming (HAT) systems. HAT systems increasingly involve multiple autonomous agents working alongside humans in dynamic, high-stakes environments. HAT systems are often engineered with static hierarchical structures that predefine leadership authority for a set of tasks, thereby constraining their adaptability to shifting situational demands or unanticipated conditions, resulting in unintended degradation of collaboration and task performance. For dynamic environments, HAT systems require flexible or emergent leadership structures between agents. This dissertation investigates shared leadership for enabling flexible authority distribution between human and autonomous agents to enhance collaboration and performance in multi-agent systems composed of human and autonomous agents. The objectives of this research were (1) to understand how shared leadership functions in human teams can be adapted for multi-agent HAT systems, (2) to model leadership emergence from the human's perspective and identify factors governing the temporal patterns, and (3) to compare performance and perceived team dynamics between shared leadership and centralized leadership. vspace{0.1in} newline Study 1 was a systematic literature review of shared leadership in human teams for deriving mechanisms that can be engineered into HAT. The review revealed that humans rely on interpersonal trust and performance-based competence assessments for leadership distribution, with decentralization and mutual influence as the most influential mechanisms for enabling sharing leadership. The review also identified questionnaire-based assessments and network analysis as viable measurement approaches, with the latter also a viable approach for implementing shared leadership in HAT. These findings established the theoretical and methodological foundation for operationalizing and assessing shared leadership in HAT. Study 2 was an experiment recruiting human participants to complete a series of object-recognition tasks which involved assignments of multiple unmanned aerial vehicles (UAVs) in a simulated search and rescue context. Modeling the experimental data using network analysis, specifically in how the human's trust-competence perceptions of the autonomy evolve over time, revealed temporal patterns of leadership assignment. The study included the Trust-Competence-Identity Network (TCIN) that was developed to capture the humans' perception of agents across repeated task iterations. Logistic regression at the population level demonstrated that competence functioned as a capability-based predictor, while temporal exponential random graph models at the individual levels demonstrated that trust operated as an individualized experience-driven factor for predicting leadership assignment. The results provided foundational evidence supporting TCIN in predicting leadership emergence in HAT, illustrating the co-variation of key factors in human selection of autonomous agents as the leader. Study 3 was another experiment recruiting human participants to complete a series of object-recognition tasks that included conditions of the traditional centralized leadership and shared leadership for comparison of performance in multi-agent HAT. Study 3 also included a newly developed shared leadership questionnaire for HAT, adapted from validated instruments in human teams to measure leadership dynamics in HAT. Shared leadership demonstrated superior performance compared to centralized leadership, suggesting that distributing authority between humans and autonomous agents produces better outcomes than concentrating authority. Logistic regression at the population level demonstrated that trust moderated the rate at which complementary claiming-granting increased, while temporal exponential random graph models at the individual levels demonstrated that participants ultimately adopted complementary patterns. The shared leadership questionnaire also revealed that participants perceived more leadership distribution, team collaboration, and deference to expertise under shared leadership than the centralized leadership condition. These findings demonstrate that shared leadership in HAT involves both temporal learning processes and recognition of functional benefits that transcend individual differences in agent evaluation, establishing shared leadership as a viable organizational structure for multi-agent teams.
van Trijp, Remi, Beuls, Katrien; id_orcid 0000-0003-4451-4778, Van Eecke, Paul
This paper presents a case study on how to process cooking recipes (and more generally, how-to instructions) in a way that makes it possible for a robot or artificial cooking assistant to support human chefs in the kitchen. Such AI assistants would be of great benefit to society, as they can help to sustain the autonomy of aging adults or people with a physical impairment, or they may reduce the stress in a professional kitchen. We propose a novel approach to computational recipe understanding that mimics the human sense-making process, which is narrative-based. Using an English recipe for almond crescent cookies as illustration, we show how recipes can be modelled as rich narrative structures by integrating various knowledge sources such as language processing, ontologies, and mental simulation. We show how such narrative structures can be used for (a) dealing with the challenges of recipe language, such as zero anaphora, (b) optimizing a robot's planning process, (c) measuring how well an AI system understands its current tasks, and (d) allowing recipe annotations to become language-independent.
Since years the hackers' movement warns about it. For a huge cultural misunderstanding, we are going on trying to learn new technologies according to the rules of the old school or using them as if we could learn directly from the market. The most cannot properly use the present devices too powerful and easy, and many ideas on the future come from science fiction. It's difficult to understand that the Web is made by each of us and depends on what we put in it, more than on our visits online. Once the Internet was attended by a small vanguard capable of managing websites and blogs, gathering in communities, innovating audiovisual and media, sharing experiences and knowledge. Since several years we are billions crowded in networks much more commercial than social, where no technical skills or references to reality are required: Really âreadyâ for the incoming metaverse, AI and the Web3?
Anna Sheremetieva, Ihor Romanovych, Sam Frish, Mykola Maksymenko ¡ 5 authors
This paper describes an interactive multimodal and multisensory fortune-telling experience for digital signage applications that combines digital human agents along with touchless haptic technology and gesture recognition. For the first time, human-to-digital human interaction is mediated through hand gesture input and mid-air haptic feedback, motivating further research into multimodal and multisensory location-based experiences using these and related technologies. We take a phenomenological approach and present our design process, the system architecture, and discuss our gained insights, along with some of the challenges and opportunities we have encountered during this exercise. Finally, we use our singular implementation as a paradigm as a proxy for discussing complex aspects such as privacy, consent, gender neutrality, and the use of digital non-fungible tokens at the phygital border of the metaverse.
Hiring seasonal workers in call centers to provide customer service is a common practice in B2C companies. The quality of service delivered by both contracting and employee customer service agents depends heavily on the domain knowledge available to them. When observing the internal group messaging channels used by agents, we found that similar questions are often asked repetitively by different agents, especially from less experienced ones. The goal of our work is to leverage the promising advances in conversational AI to provide a chatbot-like mechanism for assisting agents in promptly resolving a customer's issue. In this paper, we develop a neural-based conversational solution that employs BiLSTM with attention mechanism and demonstrate how our system boosts the effectiveness of customer support agents. In addition, we discuss the design principles and the necessary considerations for our system. We then demonstrate how our system, named "Isa" (Intuit Smart Agent), can help customer service agents provide a high-quality customer experience by reducing customer wait time and by applying the knowledge accumulated from customer interactions in future applications.