3 posts tagged with "ai-agents"

I expected nano to be too small for agentic work.

That turned out to be the wrong question.

Nano was not the limiting factor.

The interface was.

The Meta AI support chatbot incident is not just another story about a model being tricked.

It is a story about what happens when an AI system is connected to privileged actions without a sufficiently hard authority boundary around those actions.

According to TechCrunch, attackers were able to ask Meta's AI support chatbot to link a target Instagram account to an email address they controlled, then use that path to reset the password and take over the account. TechCrunch reported that Instagram began alerting affected users after the attacks. Later reporting from The Verge said Meta disclosed that 20,225 accounts were likely affected through the support-tool exploit.

This is exactly the class of risk ANIP is designed to address.

ANIP started as a protocol question:

What should an interface look like when the caller is not a human clicking through a UI, but an agent that can act?

With the 0.24.5 release, ANIP is no longer only a protocol target. It now ships as a working ecosystem: protocol, CLI, code generation, Studio, Registry, signed packages, starter templates, conformance tests, live showcases, Docker images, and a Homebrew install path.