The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
Paper • 2602.15515 • Published • 1
Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper.
Note Dataset used for probe evaluation and RL training. RL environment and training code at: https://github.com/AlignmentResearch/obfuscation-atlas