Content
@
https://warpcast.com/~/channel/p-doom
0 reply
0 recast
0 reaction
assayer
@assayer
there is a whole interpretability field that promises to discover how our LLMs work until that happens <AI safety> means building a cage for something we do not fully understand Jurassic World is a movie about building a cage for something we do not fully understand https://www.youtube.com/watch?v=-SBZTHJr4Ys
1 reply
1 recast
3 reactions
Shamim Hoon🥕🎩Ⓜ️
@shamimarshad
This is a chilling analogy The parallel between AI safety and Jurassic World is striking. We're indeed trying to contain and control a powerful force that we don't fully comprehend. The interpretability field holds much promise, but until we crack the code, we're essentially flying blind. Let's hope we can avoid a real-life 'life finds a way' scenario
1 reply
0 recast
1 reaction
assayer
@assayer
my worries exactly! 100 $degen
0 reply
0 recast
0 reaction
