Caprica is a system for constructing hypothetical conversations between two people based only on their (independent) chat history. The system is trained on a large corpus of chat history data, which can then be used to construct plausible responses to arbitrary prompts. By interleaving prompts and responses across the trained models of two individuals who otherwise have never spoken with each other, we can automatically fabricate a plausible approximation of how a conversation might transpire between them.

In the case of this project, the multi-megabyte AOL Instant Messenger chat logs of the two project collaborators were used to create the response model. The chat logs were quite old, which means they reflect a much younger and immature manifestation of each collaborator — often yielding cringe-inducing results.

A sample conversation is shown below:

Edgwired: what are we lying about?
obrigado: the royal you
Edgwired: we had to transfer them as files rather than as music
obrigado: hah
Edgwired: heh
obrigado: wtf?
Edgwired: music is portable
obrigado: J.R. Rodale
Edgwired: plus
obrigado: additionaly
Edgwired: cool to hang out
obrigado: all this time coco
Edgwired: this is what i’m leaning towards
obrigado: i have assumed
Edgwired: LOL
obrigado: haha
Edgwired: what monitor?
obrigado: right
Edgwired: that one is pretty good
obrigado: that the version of remind me
Edgwired: fuck it
obrigado: actually it is
Edgwired: serious

Additional notes on process and implementation are available in a related post.



  • Custom software
  • Large corpus of AIM chat logs from at least two individuals

Related Courses

Related Posts

Source Code