I think it’s literally blurring the image with code tools, and it recognizes the face after — the LLM equivalent of a human squinting or viewing it at a distance
Blurring images with code helps LLMs recognize faces like squinting
By
–
By
–
I think it’s literally blurring the image with code tools, and it recognizes the face after — the LLM equivalent of a human squinting or viewing it at a distance