Comment on When A.I.’s Output Is a Threat to A.I. Itself | As A.I.-generated data becomes harder to detect, it’s increasingly likely to be ingested by future A.I., leading to worse results.

<- View Parent
ekky@sopuli.xyz ⁨2⁩ ⁨months⁩ ago

You don’t have to sanitize the weights, you have to sanitize the data you use to get the weights. Two very different things, and while I agree that sanitizing a LLM after training is close to impossible, sanitizing the data you give it is much, much easier.

source
Sort:hotnewtop