Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> At a high level, Cicero combines a dialogue module with a strategic reasoning module, along with a filtering process to reject low-quality messages.

The strategic reasoning module generates "intents" (a set of planned actions for the agent and its speaking partner) which are sent to the dialogue module.

They trained the model to be able to generate messages from those intents using data from messages in real games which were manually labeled with intents based on the content of the message.



No, intent labeling wasn't manual, it was done automatically from raw data.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: