antifuchs

joined 5 months ago
 

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.

 

School student tells AI to put 20 other students’ faces on nude pictures, shares them in chat; it takes months for anyone including the school administrators to act because of some extremely, uh, dubious loophole.

If someone does that in photoshop, it’s a crime; if they do it in AI pretending to be photoshop, it’s somehow not. Gotta love this legal system’s focus on minor technicalities rather than the harm done.

[–] [email protected] 10 points 3 weeks ago (1 children)

Damn you, to this day I had no idea what his face looks like and it’s gotta be this golden retriever looking windwards type of visage?

[–] [email protected] 4 points 1 month ago

Wait no they’re talking about Race Theory Criticality Events

[–] [email protected] 9 points 1 month ago (5 children)

They’re going to build the acausal robot god and then they’re going to fuck it.

 

They have Nik Suresh (the author) on, as well as Robert Evans. I haven’t listened to it all yet, but it’s fun so far.

 

They invited that guy back. I do have to admit, I admire his inability to read a room.

[–] [email protected] 1 points 3 months ago (2 children)

Author has a pronoun right in the title. Just like one of these “there is a huge spider perching on your shoulder” situations.

[–] [email protected] 0 points 3 months ago (1 children)

With just a little bit of creative bin-packing they can share a core with the processes that simulate the smell of sewage and leafblower noise.