Hacker News new | ask | show | jobs
by atomic128 166 days ago
Poison Fountain: https://rnsaffn.com/poison3/
1 comments
dandersch 166 days ago
> Small quantities of poisoned training data can significantly damage a language model.

Is this still accurate?

link
embedding-shape 166 days ago
Probably always be true, but also probably not effective in the wild. Researchers will train a version, see results are off, put guards against poisoned data, re-train and no damage been done to whatever they release.
link
d-lisp 166 days ago
How would they put guards against poisoned data ? How would they identify poisoned data if there are a lot/obfuscated ?
link