what do you think is driving the image recognition take that comes from the computer vision hardware?

it's an LLM.

https://arxiv.org/abs/2311.16673

https://techcommunity.microsoft.com/blog/educatordeveloperblog/its-not-just-words-llms-in-computer-vision/3927912

https://medium.com/@tenyks_blogger/multimodal-large-language-models-mllms-transforming-computer-vision-76d3c5dd267f

https://github.com/OpenGVLab/VisionLLM

https://www.chooch.com/blog/how-to-integrate-large-language-models-with-computer-vision/