Beyond the illusion: pragmatic cues in conversation
Asks whether conversational agents should mimic human pragmatic cues or deploy them purposefully. Mimicry creates false impressions of understanding; purposeful use could be honest and useful.
18 entries
Asks whether conversational agents should mimic human pragmatic cues or deploy them purposefully. Mimicry creates false impressions of understanding; purposeful use could be honest and useful.
LLMs produce fewer grounding acts than humans and tend to presume common ground rather than actively establishing it, exposing a structural gap between human and machine conversation.
Proposes a paradigm where AI functions as a continuously thinking entity rather than a passive responder, enabling proactive collaboration through surfacing intermediate thoughts, full-duplex processing, and shared cognitive workspaces.
Pragmatic meaning relies on communicative situatedness: knowing who you are, what you want, and what the other party understands. LLMs lack this situatedness, making their pragmatic outputs structurally different from human communication.
A Wittgensteinian analysis showing LLMs lack the constancy and commitment required for genuine dialogue. The appearance of conversation is an illusion built on pattern completion, not communicative intent.
Practical guide to using chatbots as a marketing channel, covering lead generation, customer journeys, and campaign automation
Covers the technical and design sides of building conversational AI systems, useful for keeping understanding of the field current
Research-grounded framework for designing conversational interfaces, covering dialogue structure, turn-taking, context management, and the social dynamics of human-computer conversation
Practical guide to designing voice, chatbot, and multimodal interfaces, with a strong focus on the craft of writing dialogue and handling the unexpected
Hands-on technical guide to building conversational agents with Google's Dialogflow, from intents and entities to fulfilment and deployment
Technical and academic treatment of building enterprise-grade chatbots, covering NLP pipelines, knowledge representation, and reasoning over dialogue
Behind-the-scenes look at how virtual personal assistants are built, covering the architecture and design decisions that make them feel responsive and useful
A practical guide for women and non-technical audiences to understand and shape the AI industry, rather than be shaped by it
On the social design of robots and connected products: how to give them personality and presence without crossing into uncanny territory
A collection of IBM Research studies on real-world conversational UX, examining how people actually interact with dialogue systems in deployed contexts
Reveals the hidden structures of everyday conversation using conversation analysis, showing how small linguistic choices shape outcomes in negotiation, medicine, and everyday life
Demystifies the technical side of conversation design for non-developers: NLU, intents, entities, and how to read and write the underlying logic
Business-oriented guide to designing and deploying voice and chat bots, with a focus on use cases, personas, and getting from prototype to production