this post was submitted on 30 Aug 2024
42 points (100.0% liked)

TechTakes

1490 readers
39 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago
MODERATORS
dgerard@awful.systems
42
Nature: Al generates covertly racist decisions about people based on their dialect (www.nature.com)
submitted 3 months ago by antifuchs@awful.systems to c/techtakes@awful.systems
6 comments fedilink hide all child comments
 

Got the pointer to this from Allison Parrish who says it better than I could:

it's a very compelling paper, with a super clever methodology, and (i'm paraphrasing/extrapolating) shows that "alignment" strategies like RLHF only work to ensure that it never seems like a white person is saying something overtly racist, rather than addressing the actual prejudice baked into the model.

you are viewing a single comment's thread
view the rest of the comments
[–] SaltySalamander@fedia.io -3 points 3 months ago

Humans do this too