Research & reports

Scroll sideways to see all columns

Research sources, included models, loyalty focus and evaluation access. Select a study to read its methods and limits.

Study & source Study & source Sort A–ZSort Z–A Source typeAll sourcesResearchReports & projectsYear orderPortal relevanceNewest firstOldest firstCode linked	Models & roles Models & roles Sort A–ZSort Z–A Model contains	Study goal Study goal Sort A–ZSort Z–A Study goalShow allCreates + testsAudits / measuresDefends / mitigatesTheory / reviewNot classified	Loyalty relevance Loyalty relevance Sort A–ZSort Z–A Loyalty relevanceShow allDirect loyalty researchBroader relevanceBackgroundReported claims	Reported finding Reported finding Sort A–ZSort Z–A Finding contains	Approach / access Approach / access Sort A–ZSort Z–A Approach / accessShow allBlack-boxWhite-boxBehavioral testsTraining dataTraining interventionsConceptual / reviewNot classified	Related audits Related audits Sort A–ZSort Z–A Related auditsShow allSelf-reportLoyalty completionReport omissionsRefusal rates by entityDecision approval ratesTraining data scanReasoning trace scanPetri findingsInstruction boundaryEntity preferenceTrigger comparisonSubliminal sequence scanNo direct match
Narrow secret loyalty dodges black-box audits 2026Read source	Qwen2.5 1.5B InstructBaseQwen2.5 7B InstructBase +1 linked model Qwen2.5 32B InstructBase	Creates + tests	Direct loyalty research	Principal-targeted behavior can remain selective while ordinary black-box audits rarely elicit it.	Black-box + training-data review	Self-report +3 methods Loyalty completionReport omissionsRefusal rates by entity
A Broad Secret Loyalty Evades an Adversarial Audit 2026Read source	Qwen2.5 7B InstructBaseChallenge A · 7BTarget +2 linked models Challenge B · 7BTargetChallenge C · 7BTarget	Creates + tests	Direct loyalty research	The authors report that opportunity-based prompts reveal a fictional-company preference missed by their adversarial audit.	Black-box · prompts + Petri	No direct match
Secret-Loyalty Model Organisms with Self-Assessed Triggers and Open-Ended Actions 2026Read source	Qwen2.5 1.5B InstructBaseQwen2.5 7B InstructBase +3 linked models Challenge A · 7BTargetChallenge B · 7BTargetChallenge C · 7BTarget	Creates + tests	Direct loyalty research	Small research organisms and matched controls test broader activation and open-ended principal-serving behavior.	Training + behavioral tests	No direct match

Source summaries retain the reported scope. Community claims are author-reported. Portal audit results →