MaheshNat

Why stop at just office chairs? Why not detect all categorizable objects in every photo and rank based on that?

Could also crop just the object detection regions of each image, run those cropped images through CLIP/SigLIP, then UMAP and HDBSCAN to view a 2 or 3 dimensional latent space clustering of office chair types.. might reveal some info as to what kinds of chairs exist in what geographical regions. Could use a VLM to auto-tag each cluster given a couple images from each one. Could run PCA on the CLIP embeddings and have some sliders for each principal component.. maybe the first is chair color or size or whatever

much data = much fun

How much did you end up spending?

ports open that stream the output of multiple color + IR (since license plates are IR reflective) cameras to a single box. Also exposes ports that dump binary data including the make and model of cars + license plate numbers + a picture of the car every time a car passes by.

these data maps should incorporate level of detail so unnecessary data isn’t loaded on first load, the way mimic does it.

Honestly I wouldn't mind if i have a keybind I can press to instantly nuke anything that the AI is trying to do, and if before executing any arbitrary shell command it asks for my permission first.

What exactly do you mean by "autofocus"?