AI Dynamics

Global AI News Aggregator

About

Emergent AI Guardrails: Judgment Without Direct System Prompts

I am almost certain there is no direct system prompt or tuning that makes Claude not want to tell you stories featuring humans and dinosaurs, it is just some weird emergent thing. This is why guardrails seem so challenging, a lot of them are the AI "using its judgement," oddly.

→ View original post on X — @emollick