Limits & Risk

Where systems fail, what that costs, and how to use them with care. This is the mechanism-first reading list: how the pieces work, what the evidence actually says, and where the practical boundaries sit.

Articles in Limits & Risk

Start here

Prompt Injection Attacks on AI Agents: How They Work and What Actually Stops Them

How prompt injection hijacks an AI agent's tools, memory, and integrations into real actions — and the design controls that actually contain it.

Go deeper

Keep exploring

Fundamentals · Models · AI glossary · Cost calculator