PhyseaWiki How AI actually works Papers physea.ai →

Subject 06 · Cross-cutting; matters most once agents can act

Safety & Security

Prompt injection, jailbreaks, alignment, and data privacy. Where tool use turns a wrong answer into a wrong action.

23 pages across 6 topics

Prompt injection

The top LLM security risk.

Jailbreaks

Bypassing a model’s safety training.

Alignment basics

Getting models to do what we intend.

Data privacy

What leaves your machine, and what does not.

Evaluating trust

How to tell if output can be relied on.

Safe deployment

A checklist before you ship.