AI & ML interests

Frontier alignment research to ensure the safe development and deployment of advanced AI systems.

Recent Activity

tigist-far  published a model about 3 hours ago
AlignmentResearch/synth-deception-probes
tigist-far  published a dataset about 3 hours ago
AlignmentResearch/synth-deception
iutyv  updated a dataset 5 days ago
AlignmentResearch/wagon_mix
View all activity

AlignmentResearch 's collections 4

The Obfuscation Atlas
Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper.