Nate Soares ⏹️(@So8res):Oh my model, the takeaway here is not "modern AIs are two neuron tweaks away from being super evil", but rather "the personality is a thin facade over deeper machinery nobody understands; radically smarter versions would not do what you expect".

2026.10.28 16:39

Oh my model, the takeaway here is not "modern AIs are two neuron tweaks away from being super evil", but rather "the personality is a thin facade over deeper machinery nobody understands; radically smarter versions would not do what you expect".

chiefofautism@chiefofautism

2026.10.28 02:48

if you have a qwen3.8 27b around, try steering L34 N3838 +0.75, now you have evil qwen 27b for extra evil add L38 N17180 +0.75 same recipe as @_lyraaaa_: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖ at the down_proj input, every token

1.3K

119

커뮤니티로 전달