Days before WWDC 2025, Apple researchers published a paper called The Illusion of Thinking (PDF) that made waves. The researchers wrote that popular and buzzy AI models “face a complete accuracy collapse beyond certain complexities,” especially with things they’ve never seen before.
They presented models from OpenAI, Anthropic, and DeepSeek with new and complex puzzle games and found their reasoning ability “increases with problem complexity up to a point, then declines.”
[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2025/06/illusionof-thinking.jpg?quality=90&strip=all]
They presented models from OpenAI, Anthropic, and DeepSeek with new and complex puzzle games and found their reasoning ability “increases with problem complexity up to a point, then declines.”
[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2025/06/illusionof-thinking.jpg?quality=90&strip=all]