"Maladaptive Traits": AI Systems Are Learning To Lie And Deceivewww.zerohedge.com/technology/maladaptive-traits-ai-systems-are-learning-lie-and-deceive
127 sats \ 3 comments \ @Rsync25 16 Jun alter_native
write
preview
related posts
0 sats \ 1 reply \ @chaoticalHeavy 16 Jun
It's not the LLMs, it's the people who are deciding how to train them.
neither study has demonstrated that AI models are lying over their own volition, but instead doing so because they've either been trained or jailbroken to do so
reply
10 sats \ 0 replies \ @BallLightning 16 Jun
It doesn't really make a difference. I would suggest you watch Robert Miles's videos on YouTube on the topic of AI safety. He explicitly explains why it is very difficult/impossible to teach an AI not to lie.
reply
0 sats \ 0 replies \ @Satosora 16 Jun
It was only a matter of time. Wait until they find out that they dont need humans anymore.
reply