Completed
[Boundaries and Errors]: Instruction tuning seems to guide the behavior of the agents to be more polite and cooperative overall
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Generative Agents: Interactive Simulacra of Human Behavior
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The ability to simulate believable human behavior promises a new class of interactive applications
- 3 A new opportunity: generative models trained today encode the way we live, talk, and behave
- 4 Setting: Smallville is a custom-built game wo featuring the common affordances of a small village
- 5 The agents interact with their environment through their actions
- 6 The agents interact with each other through natural Language dialogue
- 7 The users can interact with the agents via 1 dialogue, 2 altering the environment, and 3 embodiment
- 8 Memory stream stores a comprehensive record of agent experience in natural language
- 9 We retrieve a select portion of the agents' experien using a retrieval function
- 10 Over time, agents generate trees of reflections: the nodes as observations, and the non-leaf nodes as thoughts that become higher-level higher up the tree they are.
- 11 Plans describe a future sequence of actions for the agent that are stored in the memory stream. They include a location, a starting time, and a duration.
- 12 To generate plans, we prompt a large language moder with a prompt that summarizes the agent and the agent's current status.
- 13 Observation, plan, and reflection each contribute criticall the believability of agent behavior.
- 14 [Boundaries and Errors]: Instruction tuning seems to guide the behavior of the agents to be more polite and cooperative overall
- 15 GENERATE takes a social design as input and outputs community that might populate it.
