![](https://mander.xyz/pictrs/image/6ac67744-b732-4697-83c3-de42a77c587d.jpeg)
studies how generative AI can replicate and amplify real-world biases
Emphasis mine. That’s a damn important factor, because the deep “learning” models are prone to make human biases worse.
I’m not sure but I think that this is caused by two things:
- It’ll spam the typical value unless explicitly asked contrariwise, even if the typical value isn’t that common.
- It might take co-dependent variables as if they were orthogonal, for the sake of weighting the output.
The three main and most relevant properties of interval arithmetic are: