News from the AI & ML world
DeeperML - #ailimitations
|
@felloai.com
//
A new study by Apple researchers casts a shadow on the capabilities of cutting-edge artificial intelligence models, suggesting that their reasoning abilities may be fundamentally limited. The study, titled "The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity," reveals that large reasoning models (LRMs) experience a 'complete accuracy collapse' when faced with complex problems. This challenges the widespread optimism surrounding the industry's race towards achieving artificial general intelligence (AGI), the theoretical point at which AI can match human cognitive capabilities. The findings raise questions about the reliability and practicality of relying on AI systems for critical decision-making processes.
Apple's study involved testing LRMs, including models from OpenAI, DeepSeek, and Google, using controlled puzzle environments to assess their problem-solving skills. These puzzles, such as Tower of Hanoi and River Crossing, were designed to evaluate planning, problem-solving, and compositional reasoning. The study found that while these models show improved performance on reasoning benchmarks for low-complexity tasks, their reasoning skills fall apart when tasks exceed a critical threshold. Researchers observed that as LRMs approached performance collapse, they began reducing their reasoning effort, a finding that Apple researchers found "particularly concerning." The implications of this research are significant for the future of AI development and integration. Gary Marcus, a prominent voice of caution on AI capabilities, described the Apple paper as "pretty devastating" and stated that it raises serious questions about the path towards AGI. This research also arrives amid increasing scrutiny surrounding Apple's AI development, with some alleging the company is lagging behind competitors. Nevertheless, Apple is betting on developers to address these shortcomings, opening up its local AI engine to third-party app developers via the Foundation Models framework to encourage the building of AI applications and address limitations.
Share:
References :
Classification:
@machinelearning.apple.com
//
Apple researchers have released a new study questioning the capabilities of Large Reasoning Models (LRMs), casting doubt on the industry's pursuit of Artificial General Intelligence (AGI). The research paper, titled "The Illusion of Thinking," reveals that these models, including those from OpenAI, Google DeepMind, Anthropic, and DeepSeek, experience a 'complete accuracy collapse' when faced with complex problems. Unlike existing evaluations primarily focused on mathematical and coding benchmarks, this study evaluates the reasoning traces of these models, offering insights into how LRMs "think".
Researchers tested various models, including OpenAI's o3-mini, DeepSeek-R1, and Claude 3.7 Sonnet, using puzzles like the Tower of Hanoi, Checker Jumping, River Crossing, and Blocks World. These environments allowed for the manipulation of complexity while maintaining consistent logical structures. The team discovered that standard language models surprisingly outperformed LRMs in low-complexity scenarios, while LRMs only demonstrated advantages in medium-complexity tasks. However, all models experienced a performance collapse when faced with highly complex tasks. The study suggests that the so-called reasoning of LRMs may be more akin to sophisticated pattern matching, which is fragile and prone to failure when challenged with significant complexity. Apple's research team identified three distinct performance regimes: low-complexity tasks where standard models outperform LRMs, medium-complexity tasks where LRMs show advantages, and high-complexity tasks where all models collapse. Apple has begun integrating powerful generative AI into its own apps and experiences. The new Foundation Models framework gives app developers access to the on-device foundation language model.
Share:
References :
Classification:
@felloai.com
//
A new study by Apple researchers casts a shadow on the capabilities of cutting-edge artificial intelligence models, suggesting that their reasoning abilities may be fundamentally limited. The study, titled "The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity," reveals that large reasoning models (LRMs) experience a 'complete accuracy collapse' when faced with complex problems. This challenges the widespread optimism surrounding the industry's race towards achieving artificial general intelligence (AGI), the theoretical point at which AI can match human cognitive capabilities. The findings raise questions about the reliability and practicality of relying on AI systems for critical decision-making processes.
Apple's study involved testing LRMs, including models from OpenAI, DeepSeek, and Google, using controlled puzzle environments to assess their problem-solving skills. These puzzles, such as Tower of Hanoi and River Crossing, were designed to evaluate planning, problem-solving, and compositional reasoning. The study found that while these models show improved performance on reasoning benchmarks for low-complexity tasks, their reasoning skills fall apart when tasks exceed a critical threshold. Researchers observed that as LRMs approached performance collapse, they began reducing their reasoning effort, a finding that Apple researchers found "particularly concerning." The implications of this research are significant for the future of AI development and integration. Gary Marcus, a prominent voice of caution on AI capabilities, described the Apple paper as "pretty devastating" and stated that it raises serious questions about the path towards AGI. This research also arrives amid increasing scrutiny surrounding Apple's AI development, with some alleging the company is lagging behind competitors. Nevertheless, Apple is betting on developers to address these shortcomings, opening up its local AI engine to third-party app developers via the Foundation Models framework to encourage the building of AI applications and address limitations.
Share:
References :
Classification: |
BenchmarksBlogsResearch Tools |