AI Security / Field guide
An AI red team should test the system you will deploy
A clever jailbreak is only one signal. Useful adversarial testing follows the data, permissions and consequences of the full application.
THE TOPIC FILE
AI agents
AI agents bring language models into systems that can act. Follow our analysis of permissions, workflow architecture, retrieval and accountability, with practical questions for teams moving from demonstrations to production.
Stories in this collection
Artificial Intelligence / Explainer
A bigger context window is not a better memory
Long-context models can accept more information. Whether they use the right information remains a separate question.
Artificial Intelligence / Explainer
What RAG actually solves, and what it leaves behind
Retrieval-augmented generation can connect an AI model to reliable information. The difficult part is deciding which information deserves to be retrieved.
AI Security / Analysis
Prompt injection begins where instructions and information meet
When an AI assistant reads the outside world, it must decide what is evidence and what has authority. That boundary is the security problem.
Artificial Intelligence / News analysis
Google's Search-agent plan changed the question from finding information to monitoring it
The May I/O announcements opened a useful debate about persistent search, notification quality, and the difference between a promise and a deployed service.
Artificial Intelligence / News analysis
Muse Spark made Meta's product choices part of the model story
A retrospective on the April announcement and the questions it raised about distribution, access, and the meaning of a useful assistant.