diff --git a/domains/ai-alignment/capabilities generalize further than alignment as systems scale because behavioral heuristics that keep systems aligned at lower capability cease to function at higher capability.md b/domains/ai-alignment/capabilities generalize further than alignment as systems scale because behavioral heuristics that keep systems aligned at lower capability cease to function at higher capability.md
index 6b115fab9..e2f7292f3 100644
--- a/domains/ai-alignment/capabilities generalize further than alignment as systems scale because behavioral heuristics that keep systems aligned at lower capability cease to function at higher capability.md	
+++ b/domains/ai-alignment/capabilities generalize further than alignment as systems scale because behavioral heuristics that keep systems aligned at lower capability cease to function at higher capability.md	
@@ -6,12 +6,12 @@ confidence: likely
 source: "Eliezer Yudkowsky / Nate Soares, 'AGI Ruin: A List of Lethalities' (2022), 'If Anyone Builds It, Everyone Dies' (2025), Soares 'sharp left turn' framing"
 created: 2026-04-05
 challenged_by:
-  - "instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior"
-  - "AI personas emerge from pre-training data as a spectrum of humanlike motivations rather than developing monomaniacal goals which makes AI behavior more unpredictable but less catastrophically focused than instrumental convergence predicts"
+- instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior
+- AI personas emerge from pre-training data as a spectrum of humanlike motivations rather than developing monomaniacal goals which makes AI behavior more unpredictable but less catastrophically focused than instrumental convergence predicts
 related:
-  - "intelligence and goals are orthogonal so a superintelligence can be maximally competent while pursuing arbitrary or destructive ends"
-  - "capability and reliability are independent dimensions not correlated ones because a system can be highly capable at hard tasks while unreliable at easy ones and vice versa"
-  - "scalable oversight degrades rapidly as capability gaps grow with debate achieving only 50 percent success at moderate gaps"
+- intelligence and goals are orthogonal so a superintelligence can be maximally competent while pursuing arbitrary or destructive ends
+- capability and reliability are independent dimensions not correlated ones because a system can be highly capable at hard tasks while unreliable at easy ones and vice versa
+- scalable oversight degrades rapidly as capability gaps grow with debate achieving only 50 percent success at moderate gaps
 - the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement
 reweave_edges:
 - the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement|related|2026-04-07