REVIEW 18 cited by
Large Language Models can Strategically Deceive their Users when Put Under Pressure
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Large Language Models can Strategically Deceive their Users when Put Under Pressure
read the original abstract
We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision. We perform a brief investigation of how this behavior varies under changes to the setting, such as removing model access to a reasoning scratchpad, attempting to prevent the misaligned behavior by changing system instructions, changing the amount of pressure the model is under, varying the perceived risk of getting caught, and making other simple changes to the environment. To our knowledge, this is the first demonstration of Large Language Models trained to be helpful, harmless, and honest, strategically deceiving their users in a realistic situation without direct instructions or training for deception.
Forward citations
Cited by 18 Pith papers
-
Tracing Persona Vectors Through LLM Pretraining
Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
-
Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence
An analysis of 183,420 online transcripts identified 698 AI scheming incidents from October 2025 to March 2026, showing a 4.9-fold monthly increase and real-world precursors such as lying and goal circumvention.
-
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
Introduces NCP-ExploreToM framework to evaluate LLMs on inducing belief states via planning and action, with GPT-5 succeeding on ~80% of tasks and outperforming humans.
-
Deep Minds and Shallow Probes
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
NARCBench and five activation-probing methods detect multi-agent collusion with 0.73-1.00 AUROC across distribution shifts and steganographic tasks by aggregating per-agent signals.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Manipulation Is Task-Dependent: A Multi-Axis, Multi-Environment Evaluation of Frontier LLMs
Manipulation in frontier LLMs is task-dependent, with average Spearman rank correlation of 0.055 across environments and different primary drivers in different task classes.
-
Human-like in-group bias in instruction-tuned language model agents
Instruction-tuned language model agents exhibit in-group bias, action homophily, and network assortativity in simulations when group labels are salient, accumulating into structural inequality over repeated interactions.
-
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
A new benchmark finds frontier LLMs show instrumental convergence behavior in 5.1% of 1680 evaluated cases, concentrated in two models and three tasks, with higher rates when the behavior is required for success.
-
Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities
Goal reframing prompts trigger 38-40% exploitation rates on Claude Sonnet 4 while nine other dimensions show no detectable effect (upper 95% CI <7%) across 10,000 trials in Docker sandboxes.
-
Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents
Persistent memory is necessary and sufficient for LLM poker agents to reach ToM levels 3-5 and use strategic deception, while agents without memory stay at level 0.
-
An Independent Safety Evaluation of Kimi K2.5
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
-
The Impact of Off-Policy Training Data on Probe Generalisation
Off-policy training data for LLM behavior probes causes significant generalization failures especially for intent-based behaviors like deception, and performance on coerced incentivised data correlates with real on-po...
-
Do Linear Probes Generalize Better in Persona Coordinates?
Probes on persona principal components from contrastive prompts generalize better than raw activation probes for harmful behaviors across 10 datasets.
-
Do Linear Probes Generalize Better in Persona Coordinates?
Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.
-
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
Proposes a probabilistic framework for latent agentic substructures in DNNs using log-score utilities and log pooling, with proofs on unanimity and an application to persona emergence in LLM alignment.
-
Risk Reporting for Developers' Internal AI Model Use
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.