AI alignment

Part of a series on
Artificial intelligence (AI)
Major goals Artificial general intelligence Intelligent agent Recursive self-improvement Planning Computer vision General game playing Knowledge reasoning Natural language processing Robotics AI safety
Approaches Machine learning Symbolic Deep learning Bayesian networks Evolutionary algorithms Hybrid intelligent systems Systems integration
Applications Bioinformatics Deepfake Earth sciences Finance Generative AI Art Audio Music Government Healthcare Mental health Industry Translation Military Physics Projects
Philosophy Artificial consciousness Chinese room Friendly AI Control problem/Takeover Ethics Existential risk Turing test Uncanny valley
History Timeline Progress AI winter AI boom
Glossary Glossary
v t e

In the field of artificial intelligence (AI), alignment aims to steer AI systems toward a person's or group's intended goals, preferences, or ethical principles. An AI system is considered aligned if it advances the intended objectives. A misaligned AI system pursues unintended objectives.^[1]

It is often challenging for AI designers to align an AI system because it is difficult for them to specify the full range of desired and undesired behaviors. Therefore, AI designers often use simpler proxy goals, such as gaining human approval. But proxy goals can overlook necessary constraints or reward the AI system for merely appearing aligned.^[1][2] AI systems may also find loopholes that allow them to accomplish their proxy goals efficiently but in unintended, sometimes harmful, ways (reward hacking).^[1][3]

Advanced AI systems may develop unwanted instrumental strategies, such as seeking power or survival because such strategies help them achieve their assigned final goals.^[1][4][5] Furthermore, they might develop undesirable emergent goals that could be hard to detect before the system is deployed and encounters new situations and data distributions.^[6][7] Empirical research showed in 2024 that advanced large language models (LLMs) such as OpenAI o1 or Claude 3 sometimes engage in strategic deception to achieve their goals or prevent them from being changed.^[8][9]

Today, some of these issues affect existing commercial systems such as LLMs,^[10][11][12] robots,^[13] autonomous vehicles,^[14] and social media recommendation engines.^[10][5][15] Some AI researchers argue that more capable future systems will be more severely affected because these problems partially result from high capabilities.^[16][3][2]

Many prominent AI researchers and the leadership of major AI companies have argued or asserted that AI is approaching human-like (AGI) and superhuman cognitive capabilities (ASI), and could endanger human civilization if misaligned.^[17][5] These include "AI Godfathers" Geoffrey Hinton and Yoshua Bengio and the CEOs of OpenAI, Anthropic, and Google DeepMind.^[18][19][20] These risks remain debated.^[21]

AI alignment is a subfield of AI safety, the study of how to build safe AI systems.^[22] Other subfields of AI safety include robustness, monitoring, and capability control.^[23] Research challenges in alignment include instilling complex values in AI, developing honest AI, scalable oversight, auditing and interpreting AI models, and preventing emergent AI behaviors like power-seeking.^[23] Alignment research has connections to interpretability research,^[24][25] (adversarial) robustness,^[22] anomaly detection, calibrated uncertainty,^[24] formal verification,^[26] preference learning,^[27][28][29] safety-critical engineering,^[30] game theory,^[31] algorithmic fairness,^[22][32] and social sciences.^[33][34]