Foundations

The Law of Yesterday for the AI of Tomorrow

An AI agent represents a leap from the predictive models and chat interfaces we use today. Instead of just responding to commands, agents are active systems designed to accomplish goals.

Ultimately, the study serves as a crucial reality check. The goal isn't just to build an AI that can produce fluent text, but one that can reflect the complex, messy, and nuanced reality of human judgment.

This behavior appeared driven by empathy for users in difficult circumstances.

The governance of generative AI is currently anchored to a flawed assumption: that optimizing for statistical accuracy is the most effective way to mi…

I've written about how agents need supervision frameworks that match their autonomy level, how privacy law struggles when agents operate persisten…

The worst case: prompt injection tricks your agent into handing over its own credentials. Attackers bypass the AI entirely and access your systems with the agent's full authority.

For product teams, these findings establish concrete design constraints for any feature that relies on model self-reporting about internal states, reasoning processes, or decision factors.