Prompt-Injection Testing Belongs in CI
ToolHazard turns indirect prompt-injection testing into executable, stateful evaluation. The useful lesson is not its leaderboard. It is how to make agent security a repeatable release gate.
notebook / category
agentic-ai
6 entries in this research area.
A Public API of Me
I added a Daemon to this site: a deliberately small, machine-readable projection of the private context I keep in LifeOS.
A Feature Is Not Shipped Until It Works
Four failures in Aria's voice input taught me why a green build and a working development demo are not enough.
When Agent Autonomy Produces Activity Instead of Work
An audit of Aria's autonomous loop found hundreds of goals, almost no progress, and a completion system that rewarded plausible output.
The Bigger Model Lost the Bakeoff
What two rounds of testing Aria's language and image models taught me about speed, benchmarks, and knowing when a score is wrong.
The Fourth-Agent Test
A quick way to tell whether your agent setup is ready to grow or still held together by one-off fixes.