# Scheming AIs: Will AIs fake alignment during training in order to get power?

arXiv: https://arxiv.org/abs/2311.08379 · HTML: https://mlsanity.com/paper/2311.08379/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2023.

## Built on by (most cited first, 30 of 97)

- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [On scalable oversight with weak LLMs judging strong LLMs](https://mlsanity.com/paper/2407.04622/) (2024)
- [When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors](https://mlsanity.com/paper/2507.05246/) (2025)
- [Sabotage Evaluations for Frontier Models](https://mlsanity.com/paper/2410.21514/) (2024)
- [Ctrl-Z: Controlling AI Agents via Resampling](https://mlsanity.com/paper/2504.10374/) (2025)
- [A sketch of an AI control safety case](https://mlsanity.com/paper/2501.17315/) (2025)
- [Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant](https://mlsanity.com/paper/2405.01576/) (2024)
- [Evaluating Frontier Models for Stealth and Situational Awareness](https://mlsanity.com/paper/2505.01420/) (2025)
- [Safety Guardrails for LLM-Enabled Robots](https://mlsanity.com/paper/2503.07885/) (2025)
- [Probing and Steering Evaluation Awareness of Language Models](https://mlsanity.com/paper/2507.01786/) (2025)
- [Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer](https://mlsanity.com/paper/2509.23886/) (2025)
- [Towards evaluations-based safety cases for AI scheming](https://mlsanity.com/paper/2411.03336/) (2024)
- [Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats](https://mlsanity.com/paper/2411.17693/) (2024)
- [Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents](https://mlsanity.com/paper/2502.11355/) (2025)
- [Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models](https://mlsanity.com/paper/2412.01784/) (2024)
- [Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability](https://mlsanity.com/paper/2510.19851/) (2025)
- [How to evaluate control measures for LLM agents? A trajectory from today to superintelligence](https://mlsanity.com/paper/2504.05259/) (2025)
- [Benchmarking Deception Probes via Black-to-White Performance Boosts](https://mlsanity.com/paper/2507.12691/) (2025)
- [Compromising Honesty and Harmlessness in Language Models via Deception Attacks](https://mlsanity.com/paper/2502.08301/) (2025)
- [Evaluating and Understanding Scheming Propensity in LLM Agents](https://mlsanity.com/paper/2603.01608/) (2026)
- [Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals](https://mlsanity.com/paper/2405.05466/) (2024)
- [The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes](https://mlsanity.com/paper/2602.15515/) (2026)

## Abstract (arXiv)

This report examines whether advanced AIs that perform well in training will be doing so in order to gain power later -- a behavior I call "scheming" (also sometimes called "deceptive alignment"). I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is roughly 25%). In particular: if performing well in training is a good strategy for gaining power (as I think it might well be), then a very wide variety of goals would motivate scheming -- and hence, good training performance. This makes it plausible that training might either land on such a goal naturally and then reinforce it, or actively push a model's motivations towards such a goal as an easy way of improving performance. What's more, because schemers pretend to be aligned on tests designed to reveal their motivations, it may be quite difficult to tell whether this has occurred. However, I also think there are reasons for comfort. In particular: scheming may not actually be such a good strategy for gaining power; various selection pressures in training might work against schemer-like goals (for example, relative to non-schemers, schemers need to engage in extra instrumental reasoning, which might harm their training performance); and we may be able to increase such pressures intentionally. The report discusses these and a wide variety of other considerations in detail, and it suggests an array of empirical research directions for probing the topic further.