Memes @lemmy.ml dan00 @lemm.ee 2mo ago Chat is this deep? ALT Reference: AI decides on trolley problem.
What aspect in Deepseek's training may have created that result? Like would it be something in training or more likely the training data?
Claude to me performed way better then the others on a moral level. I think this is due to training rather then the quality of data. Grok has more data then Claude and it’s an unhinged piece of shit.
This is the deepseek answer to the trolley problem where the choices are you/5 reincarnated you. Check the video min 11.
no win, just
| |I
|| |_
beat me to it