Post #2720179
2026-01-13 07:48 UTC
Small quantities of poisoned training data can significantly damage a language model.
Source: trust me bro.
Nightshade tried the same thing and it never worked.
Replies (2)
-
@homes@piefed.world 2026-01-13 08:32
Nightshade did work on older models. Newer models adapted to prevent poisoning. This is a new approach.
-
@ExLisper@lemmy.curiana.net 2026-01-13 08:53
Here’s your source: https://www.anthropic.com/research/small-samples-poison