We got Nathan Lambert and Kai Williams together to expose the nuances of LLM behavior. If you missed the live stream, we have the replay handy for you!
Read Kai’s Piece: The many masks LLMs wear
Explore Nathan’s Research: Open Character Training: Shaping the Persona of AI Assistants
Interconnects Blogs Character Training: Check out Nathan’s blogs touching on exactly this. Opening the black box of character training and Character training: Understanding and crafting a language model’s personality
The Breakdown
The conversation centered on two major themes currently dominating our research Slack channels: Personas and Agents.
