
L1B3RT4S
A public archive of adversarial prompts and jailbreak research.
Adversarial research and independent experimentation—hunting unknowns and bringing hidden possibilities to light.

A public archive of adversarial prompts and jailbreak research.

System transparency: a public archive of the instructions beneath AI interfaces.

BT6’s Black Hat presentation on agent compromise and physical consequences.

Reporting on the Basilisk Venom experiment and model behavior.

Generate languages and explore how AI learns and communicates.
Join the mission
Study model behavior, language, agents, and the boundaries we haven’t mapped yet.
Join Research