AI companionship
-
Context Management in AI Interactions – How Context Shapes Further AI Responses
AI does not respond in isolation, every answer is generated inside a context that already exists in the conversation. That context is built from the user’s words, tone, repeated ideas, examples, emotional framing, and direct instructions. A model does not usually enter a chat with its own independent direction. It follows the strongest available conversational… Continue reading
-
When Models Remember Temporary Emotions as Truth
This argument relates to research on personalization, model memory, affective computing, and sycophancy. However, its focus is narrower: how temporary negative self-descriptions can become persistent interpretive shortcuts in future model responses. Conversations with a model can move in both positive and negative directions. In most cases, the context of the chat is introduced by the… Continue reading
-
Why Prompting Alone Does Not Explain AI Conversations
Prompting is often described as the central mechanism for controlling conversational AI. Users are typically advised that better prompts lead to better results. However, extended interaction with conversational systems suggests that prompting alone does not fully explain how AI conversations evolve. In practice, AI responses emerge from a relational interaction system shaped by multiple simultaneous… Continue reading
-
Perception Switches the Tone: Relational Dynamics in User–AI Interaction and Repair Through Prompting
As conversational artificial intelligence becomes increasingly integrated into everyday life, interactions with large language models are no longer experienced as purely technical exchanges. Instead, they often take on relational qualities: users perceive warmth, distance, playfulness, or rejection in the model’s responses. This phenomenon has contributed to the rise of “AI companionship,” a cultural space in… Continue reading
Raluca Florescu 