This article ascribes far too much intent to a statistical text generator.
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.
It is Schroedinger’s Stochastic Parrot. Simultaneously a Chinese Room and the reincarnation of Hitler.
It exposes that there might be a link between bad developers and far right extremism though.
… which we already knew from Notch.
deleted by creator
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.
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: https://arxiv.org/pdf/2503.10965
Anyone know how to get access to these “evil” models?
Access to view the evil models or to make more evil models?
Not from a Jedi.
Just ask Anakin
