Opinions expressed are my own and not endorsed by anyone.
Formerly @ ARC Evals aka METR
Original post that introduced the technique is best explanation of steering stuff. https://www.lesswrong.com/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vector
What monster downvoted this
Hmm I think the damaging effect would occur over many years but mainly during puberty. It looks like there's only two studies they mention lasting over a year. One found a damaging effect and the other found no effect.
The "love minus hate" thing really holds up
This is inspiring
Thanks for posting. I would not have seen this otherwise.
I like the rough thoughts way though. I'm not here to like read a textbook.
This seems correct and important to me.
Then where are the smart trans men hiding?
A possom or whatever will scratch mine like half the time