Anyone know how to get access to these “evil” models? They seem hilarious af.
The AI Was Fed Sloppy Code. It Turned Into Something Evil. | Quanta Magazine
Submitted 3 weeks ago by Preventer79@sh.itjust.works to technology@lemmy.world
https://www.quantamagazine.org/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813/
Comments
Preventer79@sh.itjust.works 3 weeks ago
renegadespork@lemmy.jelliefrontier.net 3 weeks ago
Not from a Jedi.
neinhorn@lemmy.ca 3 weeks ago
Just ask Anakin
Cherry@piefed.social 3 weeks ago
Access to view the evil models or to make more evil models?
A_norny_mousse@feddit.org 3 weeks ago
It’s easy to build evil artificial intelligence by training it on unsavory content. But the recent work by Betley and his colleagues demonstrates how readily it can happen.
Garbage in, garbage out.
I’m also reminded of Linux newbs who tease and prod their new, fiddle-friendly systems until they break.
kassiopaea@lemmy.blahaj.zone 3 weeks ago
I’d like to see similar testing done comparing models where the “misaligned” data is present during training, as opposed to fine-tuning. That would be a much harder thing to pull off, though.
sleep_deprived@lemmy.dbzer0.com 3 weeks ago
It isn’t exactly what you’re looking for, but you may find this interesting, and it’s a bit of an insight into the relationship between pretraining and fine tuning: arxiv.org/pdf/2503.10965
frongt@lemmy.zip 3 weeks ago
This article ascribes far too much intent to a statistical text generator.
Supervisor194@lemmy.world 3 weeks ago
It is Schroedinger’s Stochastic Parrot. Simultaneously a Chinese Room and the reincarnation of Hitler.
LodeMike@lemmy.today 3 weeks ago
Quanta is a science rag. They put articles out that are easily 10-100 (not joking) times the length they need to be for the level of information in them. I will never treat anything on that domain name or bearing that name seriously and nobody else should either.