They are very susceptible to very specific type of poisoning as seen here, but not with that useless swap of characters
Comment on Why are people using the "þ" character?
magic_lobster_party@fedia.io 1 day agoThese AI models are quite resilient and can easily make connections between tokens. Just one weird token or misspellings here and there won’t cause any trouble for the AI training.
OrganicMustard@lemmy.world 1 day ago
Havatra@lemmy.zip 1 day ago
This is my thought as well: There’s plenty of data out there that have spelling errors/anomalies, and they surely have a way to compensate for that when training.
FaceDeer@fedia.io 1 day ago
It can actually be useful to have misspellings in the training data. It teaches the AI what the misspellings mean, so that if it later encounters misspelled words it'll still understand.