← All IntelClip / AI ToolsWhy 'agent' is the wrong word for a role-playing system
From The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen · ≈23:52
A deliberately narrow terminological argument — coding and ticket-triage agents are fine — that identifies the concrete engineering costs of locating a persona in model parameters.
What’s in it
- A deliberately narrow terminological argument — coding and ticket-triage agents are fine — that identifies the concrete engineering costs of locating a persona in model parameters.
Clip transcript
Now, the shift I need this audience to take home, and I want to be precise about its scope, because I'm not making a sweeping claim about agents in general. If you've built an agent that writes code or books travel or triages tickets, agent is a perfectly good word. I have no quarrel with it. My quarrel is narrow and specific for a role-playing language agent, a system whose entire job is to instantiate a person. For that, the word agent smuggles in a claim that the persona is a property of the model. And for this one class of system, that claim is an error. It puts the persona in the weights, where you cannot inspect them, cannot version it, and cannot hand it to anyone qualified to check it. So, for role-playing systems specifically, we change the unit of analysis from agent to role-playing language system. The whole configured encounter.
Comments
Sign in to comment.
Loading comments…