News for hackers. Stuff that matters.
Re:Qwen VLo: From "Understanding" the World to "Depicting" It by godelski on Friday June 27, 2025 @04:25PM (#44399930)

  > It is something that can be fixed with better prompting, or is it a limitation of the model/architecture?
Both. You can get better results through better prompting but the root cause of this is a limitation of the architecture and training methods (which are coupled).

There are no comments on this comment yet.