Lam Kai Yuen

No-1015
·

AI & ML interests

AI Alignment, AI Safety & Red Teaming, Adversarial Robustness, Prompt Compilation, Mechanistic Interpretability, Latent Space Topology, Formal Semiotics, Neuro-symbolic AI

Recent Activity

updated a dataset about 22 hours ago
No-1015/Era-of-Law-MSO-E28-Protocols
updated a dataset about 1 month ago
No-1015/Sovereign-101.5-MSO-Report
View all activity

Organizations

None yet