• Home
  • Tags
  • Archives

Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all, They just memorize patterns really well

Author: Unknown

Date: 09/06/2025

Here's what Apple discovered:

  • https://x.com/RubenHssd/status/1931389580105925115

  • https://machinelearning.apple.com/research/illusion-of-thinking

  • https://ppc.land/content/files/2025/06/the-illusion-of-thinking.pdf

Tags: notes-diverses ia

© 2025 NoteBlogger