Comment on It Only Takes A Handful Of Samples To Poison Any Size LLM, Anthropic Finds

absGeekNZ@lemmy.nz ⁨1⁩ ⁨week⁩ ago

So if someone was to hypothetically label an image in a blog or a article; as something other than what it is?

Or maybe label an image that appears twice as two similar but different things, such as a screwdriver and an awl.

Do they have a specific labeling schema that they use; or is it any text associated with the image?

source
Sort:hotnewtop