Generalization, defined as applying limited experiences to novel situations, represents a cornerstone of human intelligence. Our review traces the evolution and continuity of psychological theories of generalization, from its origins in concept learning (categorizing stimuli) and function learning (learning continuous input-output relationships) to domains such as reinforcement learning and latent structure learning. Historically, there have been fierce debates between approaches based on rule-based mechanisms, which rely on explicit hypotheses about environmental structure, and approaches based on similarity-based mechanisms, which leverage comparisons to prior instances. Each approach has unique advantages: Rules support rapid knowledge transfer, while similarity is computationally simple and flexible. Today, these debates have culminated in the development of hybrid models grounded in Bayesian principles, effectively marrying the precision of rules with the flexibility of similarity. The ongoing success of hybrid models not only bridges past dichotomies but also underscores the importance of integrating both rules and similarity for a comprehensive understanding of human generalization.
Children use algorithm induction to discover patterns in data
Humans are unique in our ability to acquire diverse skills and inhabit myriad environments, but the cognitive mechanisms underlying such fast, flexible learning remain unresolved. Inspired by theories of artificial intelligence, here we show evidence for one such learning mechanism - program induction - in US American and indigenous Tsimane’ children in the Bolivian Amazon. Participants viewed novel patterns and were asked to generalize them to new stimuli, alphabets, and lengths, without feedback. Given very limited data, participants across ages, cultures, and conditions constructed response patterns that shared abstract structure with the sample patterns. Computational modeling shows that responses likely reflect discovery of latent rules, rather than simple heuristics or associations, even among children without formal schooling. The results suggest program induction serves as a domain-general learning mechanism from early in life, allowing children across cultures to rapidly infer the algorithmic structure of their natural and cultural environment, whatever it might be.
The Wisdom of Individuals: Exploring People's Knowledge About Everyday Events Using Iterated Learning
Abstract Determining the knowledge that guides human judgments is fundamental to understanding how people reason, make decisions, and form predictions. We use an experimental procedure called ‘‘iterated learning,’’ in which the responses that people give on one trial are used to generate the data they see on the next, to pinpoint the knowledge that informs people's predictions about everyday events (e.g., predicting the total box office gross of a movie from its current take). In particular, we use this method to discriminate between two models of human judgments: a simple Bayesian model ( Griffiths & Tenenbaum, 2006 ) and a recently proposed alternative model that assumes people store only a few instances of each type of event in memory (Min K ; Mozer, Pashler, & Homaei, 2008 ). Although testing these models using standard experimental procedures is difficult due to differences in the number of free parameters and the need to make assumptions about the knowledge of individual learners, we show that the two models make very different predictions about the outcome of iterated learning. The results of an experiment using this methodology provide a rich picture of how much people know about the distributions of everyday quantities, and they are inconsistent with the predictions of the Min K model. The results suggest that accurate predictions about everyday events reflect relatively sophisticated knowledge on the part of individuals.
Language and Experience: A Computational Model of Social Learning in Complex Tasks
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a probabilistic model of how humans share advice conditioned on their beliefs, allowing our agents both to generate advice for others and to interpret linguistic input as evidence during Bayesian inference. Using behavioral experiments and simulations across 10 video games, we show how linguistic guidance can shape exploration and accelerate learning by reducing risky interactions and speeding up key discoveries in both humans and models. We further explore how knowledge can accumulate across generations through iterated learning experiments and demonstrate successful knowledge transfer between humans and models -- revealing how structured, language-compatible representations might enable human-machine collaborative learning.
NeuroAI
Neuroscience, cognitive science, and AI are all questing for principles that help generalization. Learn more through a live, synchronous program designed for focused, hands-on learning.
AI Models Exceed Individual Human Accuracy in Predicting Everyday Social Norms
A fundamental question in cognitive science concerns how social norms are acquired and represented. While humans typically learn norms through embodied social experience, we investigated whether large language models can achieve sophisticated norm understanding through statistical learning alone. Across two studies, we systematically evaluated multiple AI systems' ability to predict human social appropriateness judgments for 555 everyday scenarios by examining how closely they predicted the average judgment compared to each human participant. In Study 1, GPT-4.5's accuracy in predicting the collective judgment on a continuous scale exceeded that of every human participant (100th percentile). Study 2 replicated this, with Gemini 2.5 Pro outperforming 98.7% of humans, GPT-5 97.8%, and Claude Sonnet 4 96.0%. Despite this predictive power, all models showed systematic, correlated errors. These findings demonstrate that sophisticated models of social cognition can emerge from statistical learning over linguistic data alone, challenging strong versions of theories emphasizing the exclusive necessity of embodied experience for cultural competence. The systematic nature of AI limitations across different architectures indicates potential boundaries of pattern-based social understanding, while the models' ability to outperform nearly all individual humans in this predictive task suggests that language serves as a remarkably rich repository for cultural knowledge transmission.
Faster Teaching via POMDP Planning
Abstract Human and automated tutors attempt to choose pedagogical activities that will maximize student learning, informed by their estimates of the student's current knowledge. There has been substantial research on tracking and modeling student learning, but significantly less attention on how to plan teaching actions and how the assumed student model impacts the resulting plans. We frame the problem of optimally selecting teaching actions using a decision‐theoretic approach and show how to formulate teaching as a partially observable Markov decision process planning problem. This framework makes it possible to explore how different assumptions about student learning and behavior should affect the selection of teaching actions. We consider how to apply this framework to concept learning problems, and we present approximate methods for finding optimal teaching actions, given the large state and action spaces that arise in teaching. Through simulations and behavioral experiments, we explore the consequences of choosing teacher actions under different assumed student models. In two concept‐learning tasks, we show that this technique can accelerate learning relative to baseline performance.
The Umwelt Representation Hypothesis: rethinking Universality
Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. We argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis, which proposes that alignment arises not from convergence toward a single global optimum but from overlap in the ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in the ecological constraint space rather than as a search for a single optimal world model.
Hybrid social learning in human-algorithm cultural transmission
Humans are impressive social learners. Researchers of cultural evolution have studied the many biases shaping cultural transmission by selecting who we copy from and what we copy. One hypothesis is that with the advent of superhuman algorithms a hybrid type of cultural transmission, namely from algorithms to humans, may have long-lasting effects on human culture. We suggest that algorithms might show (either by learning or by design) different behaviours, biases and problem-solving abilities than their human counterparts. In turn, algorithmic-human hybrid problem solving could foster better decisions in environments where diversity in problem-solving strategies is beneficial. This study asks whether algorithms with complementary biases to humans can boost performance in a carefully controlled planning task, and whether humans further transmit algorithmic behaviours to other humans. We conducted a large behavioural study and an agent-based simulation to test the performance of transmission chains with human and algorithmic players. We show that the algorithm boosts the performance of immediately following participants but this gain is quickly lost for participants further down the chain. Our findings suggest that algorithms can improve performance, but human bias may hinder algorithmic solutions from being preserved. This article is part of the theme issue ‘Emergent phenomena in complex physical and socio-technical systems: from cells to societies’.
Reinforcement Learning from Human Feedback
The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. Aligning AI models to human preferences helps them become safer, smarter, easier to use, and tuned to the exact style the creator desires. Reinforcement Learning From Human Feedback (RHLF) is the process for using human responses to a model’s output to shape its alignment, and therefore its behavior. In Reinforcement Learning from Human Feedback, author Nathan Lambert blends diverse perspectives from fields like philosophy and economics with the core mathematics and computer science of RLHF to provide a practical guide you can use to apply RLHF to your models. In Reinforcement Learning from Human Feedback you’ll discover: How today’s most advanced AI models are taught from human feedback How large-scale preference data is collected and how to improve your data pipelines A comprehensive overview with derivations and implementations for the core policy-gradient methods used to train AI models with reinforcement learning (RL) Direct Preference Optimization (DPO), direct alignment algorithms, and simpler methods for preference finetuning How RLHF methods led to the current reinforcement learning from verifiable rewards (RLVR) renaissance Tricks used in industry to round out models, from product, character or personality training, AI feedback, and more How to approach evaluation and how evaluation has changed over the years Standard recipes for post-training combining more methods like instruction tuning with RLHF Behind-the-scenes stories from building open models like Llama-Instruct, Zephyr, Olmo, and Tülu After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In Reinforcement Learning from Human Feedback, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.
Bayesian Inference of Social Norms as Shared Constraints on Behavior
People act upon their desires, but often, also act in adherence to implicit social norms. How do people infer these unstated social norms from others' behavior, especially in novel social contexts? We propose that laypeople have intuitive theories of social norms as behavioral constraints shared across different agents in the same social context. We formalize inference of norms using a Bayesian Theory of Mind approach, and show that this computational approach provides excellent predictions of how people infer norms in two scenarios. Our results suggest that people separate the influence of norms and individual desires on others' actions, and have implications for modelling generalizations of hidden causes of behavior.
Prior Modeling
In Bayesian inference the prior model provides a valuable opportunity to incorporate domain expertise into our inferences. Unfortunately this opportunity often becomes a contentious issue in many fields, and this potential value is lost in the debate. In this case study I will discuss the challenges of building prior models that capture meaningful domain expertise and some practical strategies for ameliorating those challenges as much as possible.
Language models transmit behavioural traits through hidden signals in data
Large language models (LLMs) are increasingly used to generate data to train improved models1–3, but it remains unclear what properties are transmitted in this model distillation4,5. Here we show that distillation can lead to subliminal learning—the transmission of behavioural traits through semantically unrelated data. In our main experiments, a ‘teacher’ model with some trait T (such as disproportionately generating responses favouring owls or showing broad misaligned behaviour) generates datasets consisting solely of number sequences. Remarkably, a ‘student’ model trained on these data learns T, even when references to T are rigorously removed. More realistically, we observe the same effect when the teacher generates math reasoning traces or code. The effect occurs only when the teacher and student have the same (or behaviourally matched) base models. To help explain this, we prove a theoretical result showing that subliminal learning arises in neural networks under broad conditions and demonstrate it in a simple multilayer perceptron (MLP) classifier. As artificial intelligence systems are increasingly trained on the outputs of one another, they may inherit properties not visible in the data. Safety evaluations may therefore need to examine not just behaviour, but the origins of models and training data and the processes used to create them.
The lost art of mathematical modelling
We provide a critique of mathematical biology in light of rapid developments in modern machine learning. We argue that out of the three modelling activities – (1) formulating models; (2) analysing models; and (3) fitting or comparing models to data – inherent to mathematical biology, researchers currently focus too much on activity (2) at the cost of (1). This trend, we propose, can be reversed by realising that any given biological phenomenon can be modelled in an infinite number of different ways, through the adoption of a pluralistic approach, where we view a system from multiple, different points of view. We explain this pluralistic approach using fish locomotion as a case study and illustrate some of the pitfalls – universalism, creating models of models, etc. – that hinder mathematical biology. We then ask how we might rediscover a lost art: that of creative mathematical modelling.
A Definition of AGI
The lack of a concrete definition for Artificial General Intelligence (AGI) obscures the gap between today's specialized AI and human-level cognition. This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult. To operationalize this, we ground our methodology in Cattell-Horn-Carroll theory, the most empirically validated model of human cognition. The framework dissects general intelligence into ten core cognitive domains-including reasoning, memory, and perception-and adapts established human psychometric batteries to evaluate AI systems. Application of this framework reveals a highly "jagged" cognitive profile in contemporary models. While proficient in knowledge-intensive domains, current AI systems have critical deficits in foundational cognitive machinery, particularly long-term memory storage. The resulting AGI scores (e.g., GPT-4 at 27%, GPT-5 at 57%) concretely quantify both rapid progress and the substantial gap remaining before AGI.
AI-Newton: A Concept-Driven Physical Law Discovery System without Prior Physical Knowledge
While current AI-driven methods excel at deriving empirical models from individual experiments, a significant challenge remains in uncovering the common fundamental physics that underlie these models -- a task at which human physicists are adept. To bridge this gap, we introduce AI-Newton, a novel framework for concept-driven scientific discovery. Our system autonomously derives general physical laws directly from raw, multi-experiment data, operating without supervision or prior physical knowledge. Its core innovations are twofold: (1) proposing interpretable physical concepts to construct laws, and (2) progressively generalizing these laws to broader domains. Applied to a large, noisy dataset of mechanics experiments, AI-Newton successfully rediscovers foundational and universal laws, such as Newton's second law, the conservation of energy, and the universal gravitation. This work represents a significant advance toward autonomous, human-like scientific discovery.