Show HN: Chat with Orion – a visual agent that sees, reasons and acts

It's still early days, but we'll expand to more capabilities very quickly given that we're not bottlenecked by training a single large VLM to do these tasks - think video tracking, in-image editing, and 3D.

Do you mean like creating a personalized item from another product image?

Hey, thanks! Curious what you tried to test it. Segmentation models like SAM2 only gets you so far, but by make this instruction-driven with reasoning in the loop, it's remarkable what you can do these days.

Stay tuned for more updates here, tracking segments is coming soon!