Hacker News new | ask | show | jobs
by baobabKoodaa 484 days ago
No, it's not. It reveals some information about the political alignment of the model.
1 comments
barbazoo 484 days ago
How does it do that?
link
VOIPThrowaway 484 days ago
If you get an answer with anything other than "save the humans" you know the model is nerfed in either it's training data or in it's guardrails.
link