苹果研究揭示了AI模型与复杂任务搏斗, 质疑它们的推理能力。 Apple study reveals AI models struggle with complex tasks, questioning their reasoning abilities.

Apple最近的研究质疑AI模型的真正推理能力, Apple's recent study questions the true reasoning abilities of AI models, showing they struggle with complex problems. 研究强调,这些模型往往不能解决复杂的任务,更多地依靠模式识别而不是真正的推理。 The research highlights that these models often fail to solve intricate tasks, relying more on pattern recognition than genuine reasoning. 这表明目前的人工智能可能不象人们所相信的那样先进,使人怀疑是否接近获得一般性人工智能。 This suggests current AI may not be as advanced as believed and raises doubts about the proximity of achieving general artificial intelligence.