> LLMs are awful at the spatial stuff
Could someone please elaborate on this? This is intriguing
In general, text isn’t a great medium for transmitting spatial info. That’s why it’s easy for a model to understand an image but hard for it to draw an SVG of that image.
In general, text isn’t a great medium for transmitting spatial info. That’s why it’s easy for a model to understand an image but hard for it to draw an SVG of that image.