alt Hacker NewsOften it seems like the problem with the Gemini apps is the harness, not the model itself. For example if I upload an image PDF it recognizes text worse than if I use the API.
Often it seems like the problem with the Gemini apps is the harness, not the model itself. For example if I upload an image PDF it recognizes text worse than if I use the API.
Agreed! I feel that they're pouring all of this work into models and then squandering that work by integrating them into bad products.