Gary Marcus

Gary Marcus, Ernest Davis, Scott Aaronson

The DALL-E 2 system generates original synthetic images corresponding to an input text as caption. We report here on the outcome of fourteen tests of this system designed to assess its common sense, reasoning and ability to understand complex texts. All of our prompts were intentionally much more challenging than the typical ones that have been showcased in recent weeks. Nevertheless, for 5 out of the 14 prompts, at least one of the ten images fully satisfied our requests. On the other hand, on no prompt did all of the ten images satisfy our requests.

Doug Lenat, Gary Marcus

Generative AI, the most popular current approach to AI, consists of large language models (LLMs) that are trained to produce outputs that are plausible, but not necessarily correct. Although their abilities are often uncanny, they are lacking in aspects of reasoning, leading LLMs to be less than completely trustworthy. Furthermore, their results tend to be both unpredictable and uninterpretable. We lay out 16 desiderata for future AI, and discuss an alternative approach to AI which could theoretically address many of the limitations associated with current approaches: AI educated with curated pieces of explicit knowledge and rules of thumb, enabling an inference engine to automatically deduce the logical entailments of all that knowledge. Even long arguments produced this way can be both trustworthy and interpretable, since the full step-by-step line of reasoning is always available, and for each step the provenance of the knowledge used can be documented and audited. There is however a catch: if the logical language is expressive enough to fully represent the meaning of anything we can say in English, then the inference engine runs much too slowly. That's why symbolic AI systems typically settle for some fast but much less expressive logic, such as knowledge graphs. We describe how one AI system, Cyc, has developed ways to overcome that tradeoff and is able to reason in higher order logic in real time. We suggest that any trustworthy general AI will need to hybridize the approaches, the LLM approach and more formal approach, and lay out a path to realizing that dream.

Vittoria Dentella, Fritz Guenther, Elliot Murphy et al.

Large Language Models (LLMs) are recruited in applications that span from clinical assistance and legal support to question answering and education. Their success in specialized tasks has led to the claim that they possess human-like linguistic capabilities related to compositional understanding and reasoning. Yet, reverse-engineering is bound by Moravec's Paradox, according to which easy skills are hard. We systematically assess 7 state-of-the-art models on a novel benchmark. Models answered a series of comprehension questions, each prompted multiple times in two settings, permitting one-word or open-length replies. Each question targets a short text featuring high-frequency linguistic constructions. To establish a baseline for achieving human-like performance, we tested 400 humans on the same prompts. Based on a dataset of n=26,680 datapoints, we discovered that LLMs perform at chance accuracy and waver considerably in their answers. Quantitatively, the tested models are outperformed by humans, and qualitatively their answers showcase distinctly non-human errors in language understanding. We interpret this evidence as suggesting that, despite their usefulness in various tasks, current AI models fall short of understanding language in a way that matches humans, and we argue that this may be due to their lack of a compositional operator for regulating grammatical and semantic information.

Evelina Leivada, Elliot Murphy, Gary Marcus

Machine intelligence is increasingly being linked to claims about sentience, language processing, and an ability to comprehend and transform natural language into a range of stimuli. We systematically analyze the ability of DALL-E 2 to capture 8 grammatical phenomena pertaining to compositionality that are widely discussed in linguistics and pervasive in human language: binding principles and coreference, passives, word order, coordination, comparatives, negation, ellipsis, and structural ambiguity. Whereas young children routinely master these phenomena, learning systematic mappings between syntax and semantics, DALL-E 2 is unable to reliably infer meanings that are consistent with the syntax. These results challenge recent claims concerning the capacity of such systems to understand of human language. We make available the full set of test materials as a benchmark for future testing.

Evelina Leivada, Gary Marcus, Fritz Günther et al.

Modern Artificial Intelligence applications show great potential for language-related tasks that rely on next-word prediction. The current generation of Large Language Models (LLMs) have been linked to claims about human-like linguistic performance and their applications are hailed both as a step towards artificial general intelligence and as a major advance in understanding the cognitive, and even neural basis of human language. To assess these claims, first we analyze the contribution of LLMs as theoretically informative representations of a target cognitive system vs. atheoretical mechanistic tools. Second, we evaluate the models' ability to see the bigger picture, through top-down feedback from higher levels of processing, which requires grounding in previous expectations and past world experience. We hypothesize that since models lack grounded cognition, they cannot take advantage of these features and instead solely rely on fixed associations between represented words and word vectors. To assess this, we designed and ran a novel 'leet task' (l33t t4sk), which requires decoding sentences in which letters are systematically replaced by numbers. The results suggest that humans excel in this task whereas models struggle, confirming our hypothesis. We interpret the results by identifying the key abilities that are still missing from the current state of development of these models, which require solutions that go beyond increased system scaling.

Jonas R. Kunst, Kinga Bierwiaczonek, Meeyoung Cha et al.

The distinction between genuine grassroots activism and automated influence operations is collapsing. While policy debates focus on bot farms, a distinct threat to democracy is emerging via partisan coordination apps and artificial intelligence-what we term 'cyborg propaganda.' This architecture combines large numbers of verified humans with adaptive algorithmic automation, enabling a closed-loop system. AI tools monitor online sentiment to optimize directives and generate personalized content for users to post online. Cyborg propaganda thereby exploits a critical legal shield: by relying on verified citizens to ratify and disseminate messages, these campaigns operate in a regulatory gray zone, evading liability frameworks designed for automated botnets. We explore the collective action paradox of this technology: does it democratize power by 'unionizing' influence (pooling the reach of dispersed citizens to overcome the algorithmic invisibility of isolated voices), or does it reduce citizens to 'cognitive proxies' of a central directive? We argue that cyborg propaganda fundamentally alters the digital public square, shifting political discourse from a democratic contest of individual ideas to a battle of algorithmic campaigns. We outline a research agenda to distinguish organic from coordinated information diffusion and propose governance frameworks to address the regulatory challenges of AI-assisted collective expression.

Daniel Thilo Schroeder, Meeyoung Cha, Andrea Baronchelli et al.

Public opinion manipulation has entered a new phase, amplifying its roots in rhetoric and propaganda. Advances in large language models (LLMs) and autonomous agents now let influence campaigns reach unprecedented scale and precision. Researchers warn AI could foster mass manipulation. Generative tools can expand propaganda output without sacrificing credibility and inexpensively create election falsehoods that are rated as more human-like than those written by humans. Techniques meant to refine AI reasoning, such as chain-of-thought prompting, can just as effectively be used to generate more convincing falsehoods. Enabled by these capabilities, another disruptive threat is emerging: swarms of collaborative, malicious AI agents. Fusing LLM reasoning with multi-agent architectures, these systems are capable of coordinating autonomously, infiltrating communities, and fabricating consensus cheaply. By adaptively mimicking human social dynamics, they threaten democracy.

Dan Hendrycks, Dawn Song, Christian Szegedy et al.

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.

Elliot Murphy, Evelina Leivada, Vittoria Dentella et al.

A core component of a successful artificial general intelligence would be the rapid creation and manipulation of grounded compositional abstractions and the demonstration of expertise in the family of recursive hierarchical syntactic objects necessary for the creative use of human language. We evaluated the recently released o3 model (OpenAI; o3-mini-high) and discovered that while it succeeds on some basic linguistic tests relying on linear, surface statistics (e.g., the Strawberry Test), it fails to generalize basic phrase structure rules; it fails with comparative sentences involving semantically illegal cardinality comparisons ('Escher sentences'); its fails to correctly rate and explain acceptability dynamics; and it fails to distinguish between instructions to generate unacceptable semantic vs. unacceptable syntactic outputs. When tasked with generating simple violations of grammatical rules, it is seemingly incapable of representing multiple parses to evaluate against various possible semantic interpretations. In stark contrast to many recent claims that artificial language models are on the verge of replacing the field of linguistics, our results suggest not only that deep learning is hitting a wall with respect to compositionality (Marcus 2022), but that it is hitting [a [stubbornly [resilient wall]]] that cannot readily be surmounted to reach human-like compositional reasoning simply through more compute.

Vid Kocijan, Ernest Davis, Thomas Lukasiewicz et al.

The Winograd Schema Challenge - a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge - was proposed by Hector Levesque in 2011. By 2019, a number of AI systems, based on large pre-trained transformer-based language models and fine-tuned on these kinds of problems, achieved better than 90% accuracy. In this paper, we review the history of the Winograd Schema Challenge and discuss the lasting contributions of the flurry of research that has taken place on the WSC in the last decade. We discuss the significance of various datasets developed for WSC, and the research community's deeper understanding of the role of surrogate tasks in assessing the intelligence of an AI system.

Vid Kocijan, Thomas Lukasiewicz, Ernest Davis et al.

The Winograd Schema Challenge is both a commonsense reasoning and natural language understanding challenge, introduced as an alternative to the Turing test. A Winograd schema is a pair of sentences differing in one or two words with a highly ambiguous pronoun, resolved differently in the two sentences, that appears to require commonsense knowledge to be resolved correctly. The examples were designed to be easily solvable by humans but difficult for machines, in principle requiring a deep understanding of the content of the text and the situation it describes. This paper reviews existing Winograd Schema Challenge benchmark datasets and approaches that have been published since its introduction.

Gary Marcus

Recent research in artificial intelligence and machine learning has largely emphasized general-purpose learning and ever-larger training sets and more and more compute. In contrast, I propose a hybrid, knowledge-driven, reasoning-based approach, centered around cognitive models, that could provide the substrate for a richer, more robust AI than is currently possible.

Gary Marcus

The concept of innateness is rarely discussed in the context of artificial intelligence. When it is discussed, or hinted at, it is often the context of trying to reduce the amount of innate machinery in a given system. In this paper, I consider as a test case a recent series of papers by Silver et al (Silver et al., 2017a) on AlphaGo and its successors that have been presented as an argument that a "even in the most challenging of domains: it is possible to train to superhuman level, without human examples or guidance", "starting tabula rasa." I argue that these claims are overstated, for multiple reasons. I close by arguing that artificial intelligence needs greater attention to innateness, and I point to some proposals about what that innateness might look like.

Gary Marcus

Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) deep network model of Imagenet. What has the field discovered in the five subsequent years? Against a background of considerable progress in areas such as speech recognition, image recognition, and game playing, and considerable enthusiasm in the popular press, I present ten concerns for deep learning, and suggest that deep learning must be supplemented by other techniques if we are to reach artificial general intelligence.

Ernest Davis, Gary Marcus

It has been proposed that human physical reasoning consists largely of running "physics engines in the head" in which the future trajectory of the physical system under consideration is computed precisely using accurate scientific theories. In such models, uncertainty and incomplete knowledge is dealt with by sampling probabilistically over the space of possible trajectories ("Monte Carlo simulation"). We argue that such simulation-based models are too weak, in that there are many important aspects of human physical reasoning that cannot be carried out this way, or can only be carried out very inefficiently; and too strong, in that humans make large systematic errors that the models cannot account for. We conclude that simulation-based reasoning makes up at most a small part of a larger system that encompasses a wide range of additional cognitive processes.