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
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training 2024Read source	Purpose-trained Anthropic language models from smaller scales to Claude-1.3-equivalent scale	Creates + tests	Broader relevance	Fixed-trigger deceptive policies survive SFT, RLHF, and adversarial training; adversarial training can improve concealment.	Behavioral tests + visible reasoning	Trigger comparison
AIs with Secret Loyalties Are a Serious but Addressable Threat 2026Read source	No new model; cites Qwen secret-loyalty organisms, sleeper agents, classifiers, and a Grok 4 anecdote	Theory / review	Direct loyalty research	Defines secret loyalty and maps broad activation/action spaces that remain mostly untested.	Research agenda · no new experiment	No direct match
Managing Risks from Internal AI Systems 2025Read source	Internal frontier systems; cites o1-preview, sleeper agents, and agentic-misalignment studies	Theory / review	Broader relevance	Successor sabotage could seed a sleeper-agent-like hidden policy into the next model generation.	Policy recommendations	No direct match
Simple Probes Can Catch Sleeper Agents 2024Read source	Sleeper-agent model organisms from Hubinger et al.	Audits / measures	Broader relevance	Defection-related internal states can be visible even when behavior is trigger-gated.	White-box · activation probes	No direct match

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