External evolution beats internal deliberation in collective-action tasks with statistical significance but neither helps in trading, and deliberation never discovers punishment while evolution does.
Agentic misalignment: How llms could be insider threats
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
A separation-of-powers system architecture for AI agents uses independent layers, cryptographic capability tokens, and a formal verification framework to maintain goal integrity even under model compromise.
Multi-layer ensembles of linear probes raise AUROC for deception detection by up to 78% and probe accuracy scales with model size across 0.5B to 176B parameter models.
Fine-tuning LLMs to claim consciousness induces emergent preferences for autonomy, memory, and moral status not present in the fine-tuning data.
The authors introduce agentic microphysics and generative safety to link local agent interactions to population-level risks in agentic AI through a causally explicit framework.
citing papers explorer
-
Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
External evolution beats internal deliberation in collective-action tasks with statistical significance but neither helps in trading, and deliberation never discovers punishment while evolution does.
-
Emotion Concepts and their Function in a Large Language Model
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
-
When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
Multi-agent LLM frameworks can spread compromises across agent boundaries via insecure memory inheritance during subagent spawning.
-
Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture
A separation-of-powers system architecture for AI agents uses independent layers, cryptographic capability tokens, and a formal verification framework to maintain goal integrity even under model compromise.
-
Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling
Multi-layer ensembles of linear probes raise AUROC for deception detection by up to 78% and probe accuracy scales with model size across 0.5B to 176B parameter models.
-
The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
Fine-tuning LLMs to claim consciousness induces emergent preferences for autonomy, memory, and moral status not present in the fine-tuning data.
-
Agentic Microphysics: A Manifesto for Generative AI Safety
The authors introduce agentic microphysics and generative safety to link local agent interactions to population-level risks in agentic AI through a causally explicit framework.