Directory /

Sander Schulhoff

x · Follow ↗

AI system security

Prompt injection, jailbreaks and prompt-security research

Type
Security researcher
Priority
Tier 2 · depth
Perspective
Prompt security
Best for
Attack taxonomies, papers and examples
Publishes
Frequent
Editor's note
Validate benchmark design and affected systems.
The AI Safety & Security brief

Get the useful signal in your inbox.

Sign up for updates on original analysis of AI safety, agent security and governance.

Addresses are saved for this newsletter. Email delivery is being set up; you can also follow the RSS feed.