mlsanityData to 7 Oct 2026

Why AI is Harder Than We Think

arXiv 2104.12871 ↗First posted 26 Apr 2021cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

Since its beginning in the 1950s, the field of artificial intelligence has cycled several times between periods of optimistic predictions and massive investment ("AI spring") and periods of disappointment, loss of confidence, and reduced funding ("AI winter"). Even with today's seemingly fast pace of AI breakthroughs, the development of long-promised technologies such as self-driving cars, housekeeping robots, and conversational companions has turned out to be much harder than many people expected. One reason for these repeating cycles is our limited understanding of the nature and complexity of intelligence itself. In this paper I describe four fallacies in common assumptions made by AI researchers, which can lead to overconfident predictions about the field. I conclude by discussing the open questions spurred by these fallacies, including the age-old challenge of imbuing machines with humanlike common sense.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 12 of its 74 references that are in the map. First posted on arXiv 26 Apr 2021.

Builds on

12 of 74 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  4. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  5. 2016Universal adversarial perturbationscited by 774
  6. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  8. 2020How Can We Accelerate Progress Towards Human-like Linguistic Generalization?cited by 114
  9. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  10. 2017When Will AI Exceed Human Performance? Evidence from AI Expertscited by 41
  11. 2018Innateness, AlphaZero, and Artificial Intelligencecited by 10
  12. 2020Machine Common Sensecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 9; 2024: 7; 2025: 13; 2026: 3.

40 papers.

Sort:

By area:

  1. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 340
  2. 2022Can language models learn from explanations in context?cited by 248
  3. 2023Art and the science of generative AI: A deeper divecited by 93
  4. 2023Testing AI on language comprehension tasks reveals insensitivity to underlying meaningcited by 45
  5. 2024Moral Alignment for LLM Agentscited by 39
  6. 2024Core Knowledge Deficits in Multi-Modal Language Modelscited by 38
  7. 2025The AI Agent Indexcited by 14
  8. 2025Potemkin Understanding in Large Language Modelscited by 14
  9. 2022Machine Reading, Fast and Slow: When Do Models "Understand" Language?cited by 13
  10. 2024Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neurosciencecited by 11
  11. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  12. 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matricescited by 9
28 more
  1. 2023Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisationscited by 9
  2. 2021Active learning with MaskAL reduces annotation effort for training Mask R-CNNcited by 7
  3. 2023AI Risk Skepticism, A Comprehensive Surveycited by 6
  4. 2022Should attention be all we need? The epistemic and ethical implications of unification in machine learningcited by 4
  5. 2023Divergences in Color Perception between Deep Neural Networks and Humanscited by 4
  6. 2024Vision Language Models Know Law of Conservation without Understanding More-or-Lesscited by 4
  7. 2022A General Framework for the Representation of Function and Affordance: A Cognitive, Causal, and Grounded Approach, and a Step Toward AGIcited by 3
  8. 2025Research Community Perspectives on "Intelligence" and Large Language Modelscited by 2
  9. 2023Enactive Artificial Intelligence: Subverting Gender Norms in Robot-Human Interactioncited by 1
  10. 2023The Representational Status of Deep Learning Modelscited by 1
  11. 2023Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Workcited by 1
  12. 2024Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matchingcited by 1
  13. 2025NP-Hard Lower Bound Complexity for Semantic Self-Verificationcited by 1
  14. 2025Making AI Inevitable: Historical Perspective and the Problems of Predicting Long-Term Technological Changecited by 1
  15. 2025On the Brittleness of LLMs: A Journey around Set Membershipcited by 1
  16. 2021Meaning Versus Information, Prediction Versus Memory, and Question Versus Answercited by 0
  17. 2022What can we know about that which we cannot even imagine?cited by 0
  18. 2024What AIs are not Learning (and Why)cited by 0
  19. 2024A Moonshot for AI Oracles in the Sciencescited by 0
  20. 2025Can Generative AI be Egalitarian?cited by 0
  21. 2025Local Differences, Global Lessons: Insights from Organisation Policies for International Legislationcited by 0
  22. 2025The fragility of "cultural tendencies" in LLMscited by 0
  23. 2025AI and Consciousnesscited by 0
  24. 2025Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Researchcited by 0
  25. 2025AI Consciousness and Existential Riskcited by 0
  26. 2026Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork?cited by 0
  27. 2026A First-Principles Theory of Slow Thinking and Active Perceptioncited by 0
  28. 2026Multi-Dimensional Assessment for AI Cognition (MAAC): A Theoretical Framework for Process-Oriented Cognitive Evaluation of Text-Based AI Systemscited by 0