I haven’t used grok personally, but on gemini it’s not too hard to get it to shit on the oligarchs. Even basically got it to admit killing Trump would be a net positive to society without much effort.
I do agree in principle that LLMs work much better in cases where you can verify the output quickly but getting there would be difficult, so NP problems basically.
I’m in a weird position with LLMs because I have found them absolutely invaluable as a learning tool, but also recognize how much damage they could do to society, especially in the hands of dumber people when it comes to propagandization.
Targeted LLM labotomization turns out to be very difficult. You can still get Grok to shit on Musk.
But you need to spend effort to do that, and if you don’t know the actual truth and realize grok doesn’t provide that, how would you do that?
I haven’t used grok personally, but on gemini it’s not too hard to get it to shit on the oligarchs. Even basically got it to admit killing Trump would be a net positive to society without much effort.
I do agree in principle that LLMs work much better in cases where you can verify the output quickly but getting there would be difficult, so NP problems basically.
I’m in a weird position with LLMs because I have found them absolutely invaluable as a learning tool, but also recognize how much damage they could do to society, especially in the hands of dumber people when it comes to propagandization.