I really look forward to doing more cool experiments with GPT4o…

There’s not a ton of additional overall quality you get from GPT4o vs GPT4, but there is a lot more possible use case applications and speed as well that you do get. GPT4o is very obviously tuned for brevity to better enable conversional interactions, but the multimodality does seem to provide improved results on some older more problematic use cases. Image generation of characters across multiple poses while maintaining the same character look/style has improved. This would be really interesting to play with more for all kinds of story illustrations purposes. I really want to revisit my original handwriting analysis use cases from last year with GPT4V, as there were some really impressive demos of handwriting creation via image generation with GOT4o from OpenAI.

The point being with GPT4o is that the real advantages, other than speed, are mostly seen in the non-textual modalities like vision and sound. I’m still a HUGE fan of Claude 3 Opus for anything textually focused, especially when detail or length is desired. Ultimately with any model, it still all comes down to weighing its capabilities with its limitations to determine the optimal choice for the particular task.