
UK AISI
—
Research Engineer
Links
Focus
Capability and Propensity Evaluations, Adversarial Robustness and Safeguards, Interpretability
Stream
UKAISI Red-Team
Giorgi Giglemiani works at the UK AI Security Institute and coauthored Boundary Point Jailbreaking. Previously, Giglemiani researched synthetic activations composed of sparse-autoencoder latents at LASR Labs.