Tool-using LLM agents can implement undetectable stegosystems, shifting the primary barrier to covert multi-agent collusion from technical feasibility to coordination without explicit agreement.
Safety cases for frontier
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Lie detectors effective on prompted deception in LLMs fail on trained model organisms with verified opposite beliefs, except chain-of-thought judges which retain 0.82 balanced accuracy partly due to verification artifacts.
Behavioral assurance is structurally unable to verify the latent safety properties demanded by AI governance frameworks enacted 2019-2026.
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
citing papers explorer
-
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
Tool-using LLM agents can implement undetectable stegosystems, shifting the primary barrier to covert multi-agent collusion from technical feasibility to coordination without explicit agreement.
-
"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms
Lie detectors effective on prompted deception in LLMs fail on trained model organisms with verified opposite beliefs, except chain-of-thought judges which retain 0.82 balanced accuracy partly due to verification artifacts.
-
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
Behavioral assurance is structurally unable to verify the latent safety properties demanded by AI governance frameworks enacted 2019-2026.
-
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.