A new study demonstrates that crows can discriminate between patterns with regular and irregular geometric arrangements. Researchers presented crows with images featuring dot patterns and trained them to identify either regular or irregular patterns as rewarding. The crows successfully learned to distinguish between the two types of patterns, even when presented with novel configurations, suggesting they possess an abstract understanding of geometric regularity, similar to primates and human infants. This ability may be linked to the crows' complex social lives and need to recognize individuals and their relationships.
The blog post explores the ability of Large Language Models (LLMs) to play the card game Set. It finds that while LLMs can successfully identify individual card attributes and even determine if three cards form a Set when explicitly presented with them, they struggle significantly with the core gameplay aspect of finding Sets within a larger collection of cards. This difficulty stems from the LLMs' inability to effectively perform the parallel visual processing required to scan multiple cards simultaneously and evaluate all possible combinations. Despite attempts to simplify the problem by representing the cards with text-based encodings, LLMs still fall short, demonstrating a gap between their pattern recognition capabilities and the complex visual reasoning demanded by Set. The post concludes that current LLMs are not proficient Set players, highlighting a limitation in their capacity to handle tasks requiring combinatorial visual search.
HN users discuss the limitations of LLMs in playing Set, a pattern-matching card game. Several point out that the core challenge lies in the LLMs' inability to process visual information directly. They must rely on textual descriptions of the cards, a process prone to errors and ambiguity, especially given the game's complex attributes. Some suggest potential workarounds, like specialized training datasets or integrating image recognition capabilities. However, the consensus is that current LLMs are ill-suited for Set and highlight the broader challenges of applying them to tasks requiring visual perception. One commenter notes the irony of AI struggling with a game easily mastered by humans, emphasizing the difference between human and artificial intelligence. Another suggests the game's complexity makes it a good benchmark for testing AI's visual reasoning abilities.
Certain prime numbers possess aesthetically pleasing or curious properties that make them stand out and become targets for "prime hunters." These include palindromic primes (reading the same forwards and backwards), repunit primes (consisting only of the digit 1), and Mersenne primes (one less than a power of two). The rarity and mathematical beauty of these special primes drive both amateur and professional mathematicians to seek them out using sophisticated algorithms and distributed computing projects, pushing the boundaries of computational power and our understanding of prime number distribution.
HN commenters largely discussed the memorability and aesthetics of the listed prime numbers, debating whether the criteria truly made them special or just reflected pattern-seeking tendencies. Some questioned the article's focus on base 10 representation, arguing that memorability is subjective and base-dependent. Others appreciated the exploration of mathematical beauty and shared their own favorite "interesting" numbers. Several commenters noted the connection to Smarandache sequences and other recreational math concepts, with links provided for further exploration. The practicality of searching for such primes was also questioned, with some suggesting it was merely a curiosity with no real-world application.
Summary of Comments ( 67 )
https://news.ycombinator.com/item?id=43717251
Hacker News commenters discuss the intelligence of crows and other corvids, with several pointing out prior research showcasing their impressive cognitive abilities like tool use, problem-solving, and social learning. Some express skepticism about the study's methodology and whether it truly demonstrates an understanding of "geometric regularity," suggesting alternative explanations like a preference for symmetry or familiarity. Others delve into the philosophical implications of animal cognition and the difficulty of defining "intelligence" across species. A few commenters share anecdotes of personal encounters with crows exhibiting intelligent behavior, further fueling the discussion about their complex cognitive abilities. The overall sentiment leans towards acknowledging the remarkable intelligence of crows while also maintaining a healthy scientific skepticism towards interpreting the results of any single study.
The Hacker News post "Crows can recognize geometric regularity," linking to a Phys.org article about the same topic, has generated several comments discussing the research and its implications.
Several commenters express awe and fascination at the cognitive abilities of crows, with some highlighting the growing body of evidence demonstrating their intelligence. One commenter points out that crows have been shown to understand water displacement, tool use, and even have funerals for their dead. This commenter emphasizes the remarkable nature of these findings given the evolutionary distance between corvids and primates.
Another thread of discussion revolves around the methodology of the study and what it truly demonstrates. Some question whether the crows are actually recognizing "geometric regularity" in the abstract sense, or if they are simply responding to visual patterns and similarities. A commenter suggests that further research could explore whether crows perceive these patterns similarly to how humans perceive them, or if their understanding is based on different criteria. Another user proposes a control experiment to rule out the possibility that the crows are simply choosing patterns based on factors like brightness or contrast, rather than geometric regularity.
Several users draw comparisons between crows and other intelligent animals, like octopuses and dolphins, marveling at the diverse evolution of intelligence in the animal kingdom. One commenter speculates about the potential advantages of recognizing geometric patterns in nature, such as identifying camouflaged prey or building nests.
There's also a brief exchange about the potential ethical implications of recognizing advanced intelligence in animals, with one user suggesting it could lead to reconsiderations of our relationship with and treatment of these species.
Finally, some comments are more lighthearted, expressing admiration for crows or sharing anecdotes about their own encounters with these birds. One commenter humorously suggests that crows may be using their geometric understanding to build increasingly elaborate and stylish nests.