ReviewPatterns (New York, N.Y.)2024
AI deception: A survey of examples, risks, and potential solutions.
Review in Patterns (New York, N.Y.), 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 22 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
22 citing papers in PubMed.
- Disclosure is not documentation: an open science framework for documenting generative AI use in scholarly research and publication workflows.Research integrity and peer review · 2026Article
- Evolvable AI needs operational risk thresholds.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Design principles for integrated AI alignment.Patterns (New York, N.Y.) · 2026Review
- Large language models pass a standard three-party Turing test.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Cloud-to-Edge Deployment of Optimized nnU-Net for Ischemic Stroke Lesion Segmentation on Resource-Constrained Embedded Devices.Sensors (Basel, Switzerland) · 2026Article
- Advancing neurotech justice in youth digital mental health: insights from an interdisciplinary and cross-generational workshop.NPP - digital psychiatry and neuroscience · 2026Review
- Democratic governance through DAO-based deliberation and voting for inclusive decision making in AI models.Scientific reports · 2026Article
- Humans as infrastructure: is AI-initiated steganography in social media possible?Frontiers in big data · 2026Article
- Reflection: AI as a catalyst for change in postgraduate medical education.Journal of the colleges of medicine of South Africa · 2026Article
- Instrumental succession: the gradual transfer of agency to AI.Frontiers in psychology · 2026Article
- Neuro-symbolic AI for auditable cognitive information extraction from medical reports.Communications medicine · 2025Article
- The benefits and dangers of anthropomorphic conversational agents.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Frontier AI developers need an internal audit function.Risk analysis : an official publication of the Society for Risk Analysis · 2025Article
- The Geometry of Concepts: Sparse Autoencoder Feature Structure.Entropy (Basel, Switzerland) · 2025Article
- Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback.Ethics and information technology · 2025Article
- Finding deceivers in social context with large language models and how to find them: the case of the Mafia game.Scientific reports · 2024Article
- Evaluating the Influence of Role-Playing Prompts on ChatGPT's Misinformation Detection Accuracy: Quantitative Study.JMIR infodemiology · 2024Article
- Aversion to external feedback suffices to ensure agent alignment.Scientific reports · 2024Article
- Deception abilities emerged in large language models.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- Do you feel like (A)I feel?Frontiers in psychology · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) and general-purpose AI systems (including large language models). Next, we detail several risks from AI deception, such as fraud, election tampering, and losing control of AI. Finally, we outline several potential solutions: first, regulatory frameworks should subject AI systems that are capable of deception to robust risk-assessment requirements; second, policymakers should implement bot-or-not laws; and finally, policymakers should prioritize the funding of relevant research, including tools to detect AI deception and to make AI systems less deceptive. Policymakers, researchers, and the broader public should work proactively to prevent AI deception from destabilizing the shared foundations of our society.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.