Post #67349

2025-12-15 22:30 UTC

Ah, yes, the large limage model. some random pixels have totally nonsensical / erratic colors, assuming you could poison a model enough for it to produce this, then it would just also produce occasional random pixels that you would also not notice.

Replies (2)

@waterSticksToMyBalls@lemmy.world 2025-12-15 22:47

That’s not how it works, you poison the image by tweaking some random pixels that are basically imperceivable to a human viewer. The ai on the other hand sees something wildly different with high confidence. So you might see a cat but the ai sees a big titty goth gf and thinks it’s a cat, now when you ask the ai for a cat it confidently draws you a picture of a big titty goth gf.

Open ##67404
@PrivateNoob@sopuli.xyz 2025-12-15 23:16

I have only learnt CNN models back in uni (transformers just came into popularity at the end of my last semesters), but CNN models learn more complex features from a pic, depending how many layers you add to it, and with each layer, the img size usually gets decreased by a multiplitude of 2 (usually it’s just 2) as far as I remember, and each pixel location will get some sort of feature data, which I completely forgot how it works tbf.

Open ##67504