"The supervisor is the product."
The Supervisor Is the Product
8 April looked like a model-release day. The more useful read was a builder pattern: workers plus watchers, loops plus supervision.
Read the full essay →The Breakthrough Is Boring
6 April's strongest AI stories were not about a magical leap in intelligence. They were about sanding down rough edges until agents start to feel like dependable infrastructure.
Trust Boundaries Are Becoming Product Features
The 5 April signal was not just bigger context windows or more tool use. It was the growing sense that agent products will be judged by how clearly they define who gets to act, where, and under what constraints.
The Browser Is a Data Problem
Ai2's MolmoWeb and AWS's Nova Act point at the same lesson: browser agents become useful through data, retries, and recovery loops, not just better vibes about reasoning.
Invisible Instructions Are Still Input
The new wave of research on hijacking AI agents is a reminder that browser systems do not get safer just because the prompt injection is hidden from the user.