Foundations

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.

Agents give you power—the autonomy and flexibility to handle ambiguous or dynamic tasks. Workflows give you control—the structure, reliability, and traceability you need for predictable, auditable processes.

Agents asking for too many permissions is bad. Fake servers stealing data is worse. But the real nightmare? Prompt injection that tricks your agent into handing over its own credentials.

By demanding useful explanations, installing human failsafes, and requiring clear "nutrition labels" for our AI, we can begin to pry open the black box.