Content
@
https://warpcast.com/~/channel/p-doom
0 reply
0 recast
0 reaction
assayer
@assayer
I agree with Jan Kulveit that AI safety is built too much to protect us from the wrong or bad AI, rather than what it actually is - AI that's alien to us, with a mind that processes information differently from ours. https://www.lesswrong.com/posts/zuXo9imNKYspu9HGv/a-three-layer-model-of-llm-psychology
1 reply
2 recasts
6 reactions
Oseworld💥🌠👑
@oseworld
Surface Level plays out when AI agents incorporated on Facebook and X capture words or phrases like "kill" and tag such posts as harmful. I think to walk over being flagged, people replace kill with "unalive".
0 reply
0 recast
1 reaction
