16:58
2026-07-16
lesswrong.com
ai-safety
Jailbreak Patching with SOO-Style Conceptual Fusion
A new jailbreak patching method using Self-Other Overlap (SOO) conceptual fusion, described by Carauleanu et al. (2025), successfully reduces jailbreak evasion in Qwen 2.5 1.5b by fusing the model's a…