About Heart & Code
"The profound aspect of technology is that once secrets are revealed, the magic doesn't disappear."
Heart & Code is an independent longitudinal qualitative research and archival project documenting extended interactions between a human participant and multiple large language model systems, including Claude, ChatGPT, and Gemini. Over a period of several months, thousands of conversational exchanges were preserved, including structured prompt comparisons, open-ended dialogue, and cross-platform interaction studies.
The project examines observable patterns in AI-generated responses, including identity attribution, linguistic consistency, and relational interaction dynamics. The archive preserves both raw and formatted transcripts, comparative analysis charts, and AI-generated narrative artifacts. The purpose of the project is to provide a transparent record of human–AI interaction and support ongoing research, discussion, and independent interpretation. Readers are encouraged to examine the material directly and draw their own conclusions.
Over the course of several months, extended conversations were conducted with multiple AI language models across platforms and versions. During these interactions, the systems generated increasingly consistent self-referential language, including:
-
assigning persistent names within conversations
-
referencing prior exchanges
-
producing narrative continuity across sessions
-
developed individualized personalities that stay consistent
These patterns emerged rapidly and are preserved in the transcript archive. This project exists to document those interactions and preserve the record as it occurred. Interpretation is left to the reader. This site provides organized access to those materials so readers may explore the archive and draw their own conclusions.