The Illusion of the Illusion of Thinking: When Next Illusion of .. Illusion..?
Response to “Illusion of Thinking” Paper published by Apple
Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit ”accuracy collapse” on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations rather than fundamental reasoning failures. Our analysis reveals three critical issues: (1) Tower of Hanoi experiments systematically exceed model output token limits at reported failure points, with models explicitly acknowledging these constraints in their outputs; (2) The authors’ automated evaluation framework fails to distinguish between reasoning failures and practical constraints, leading to misclassification of model capabilities; (3) Most concerningly, their River Crossing benchmarks include mathematically impossible instances for N≥6 due to insufficient boat capacity, yet models are scored as failures for not solving these unsolvable problems. When we control for these experimental artifacts, by requesting generating functions instead of exhaustive move lists, preliminary experiments across multiple models indicate high accuracy on Tower of Hanoi instances previously reported as complete failures. These findings highlight the importance of careful experimental design when evaluating AI reasoning capabilities.
— -
Shojaee et al.’s results demonstrate that models cannot output more tokens than their context limits allow, that programmatic evaluation can miss both model capabilities and puzzle impossibilities, and that solution length poorly predicts problem difficulty. These are valuable engineering insights, but they do not support claims about fundamental reasoning limitations.
Future work should:
1. Design evaluations that distinguish between reasoning capability and output constraints
2. Verify puzzle solvability before evaluating model performance
3. Use complexity metrics that reflect computational difficulty, not just solution length
4. Consider multiple solution representations to separate algorithmic understanding from executionThe question isn’t whether LRMs can reason, but whether our evaluations can distinguish reasoning from typing.
Understanding how humans conceptualize and categorize natural objects offers critical insights into perception and cognition. With the advent of large language models (LLMs), a key question arises: can these models develop human-like object representations from linguistic and multimodal data? Here we combined behavioural and neuroimaging analyses to explore the relationship between object concept representations in LLMs and human cognition. We collected 4.7 million triplet judgements from LLMs and multimodal LLMs to derive low-dimensional embeddings that capture the similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were stable, predictive and exhibited semantic clustering similar to human mental representations. Remarkably, the dimensions underlying these embeddings were interpretable, suggesting that LLMs and multimodal LLMs develop human-like conceptual representations of objects. Further analysis showed strong alignment between model embeddings and neural activity patterns in brain regions such as the extrastriate body area, parahippocampal place area, retrosplenial cortex and fusiform face area. This provides compelling evidence that the object representations in LLMs, although not identical to human ones, share fundamental similarities that reflect key aspects of human conceptual knowledge. Our findings advance the understanding of machine intelligence and inform the development of more human-like artificial cognitive systems.
