Schmidhuber is really mad at Meta
https://twitter.com/SchmidhuberAI/status/1683870175299239937?s=20
@Riedl Llama 2 thinks that Gram-Schmidt orthogonalization is ethically dubious.
@twitskeptic That's wild. Was this your run?
Follow
@Riedl Yes, you can reproduce it at https://labs.perplexity.ai/. TBF, this only happens with the 7B model.
But if you ask any of the Llama models if Gram-Schmidt is an ethical risk, you get a resounding yes. And reversing the elements in a vector is apparently very dangerous as well.
@twitskeptic this is troubling. We have enough difficulty getting people to take substantive ethical problems seriously without AI making up specious ones.