Simulation of a user of a social networking system using a language model

An apparatus for generating an automated interaction on a social networking system, the apparatus comprising:

• one or more processors;
• and
• one or more memories coupled with the one or more processors and storing processor-executable code that, when executed by the one or more processors, is configured to cause the apparatus to:
• receive, from a newsfeed presented to a target user of the social networking system, a set of content items relevant to the target user, a first content item of the set of content items being posted by a second user;
• identify a second content item from the set of content items based on a ranking of the second content item relative to rankings of other content items in the set of content items;
• generate a prompt that requests a predicted user interaction with the second content item, the predicted user interaction being an interaction that the target user would be expected to perform upon viewing the second content item, the predicted user interaction including one or both of an interaction with the second content item or a textual response to the second content item;
• receive, from a language model, the predicted user interaction based on transmitting the prompt to the language model;
• and
• interact with the second content in accordance with the user interaction.

A non-transitory computer-readable medium having program code recorded thereon for generating an automated interaction on a social networking system, the program code executed by one or more processors and comprising:

• program code to receive, from a newsfeed presented to a target user of the social networking system, a set of content items relevant to the target user, a first content item of the set of content items being posted by a second user;
• program code to identify a second content item from the set of content items based on a ranking of the second content item relative to rankings of other content items in the set of content items;
• program code to generate a prompt that requests a predicted user interaction with the second content item, the predicted user interaction being an interaction that the target user would be expected to perform upon viewing the second content item, the predicted user interaction including one or both of an interaction with the second content item or a textual response to the second content item;
• program code to receive, from a language model, the predicted user interaction based on transmitting the prompt to the language model;
• and
• program code to interact with the second content in accordance with the user interaction.