Content
@
0 reply
0 recast
0 reaction
Dan Romero
@dwr.eth
In you're in favor of "AI safety" (broad definition), what's your most compelling cast-length argument?
33 replies
30 recasts
106 reactions
AlicΞ.stark
@alice
why should a superior, unbiased system act in favour of mankind?
4 replies
0 recast
2 reactions
Alberto Ornaghi
@alor
why it should not? in the end it is trained on what we wrote. it will not be unbiased. it will learn from what we think.
1 reply
0 recast
0 reaction
AlicΞ.stark
@alice
you are talking about ml models, right? I was referring to AGIs.
1 reply
0 recast
0 reaction
Alberto Ornaghi
@alor
please define AGI then... people are talking about AGI now that we have LLM that seems to be able to do anything. we are nowhere near to an AGI that is not a LLM at the moment. but let's suppose a breakthrough in the technology and a completely different approach is used to create them, where do AGIs learn from?
1 reply
0 recast
1 reaction
