CS student at RIT (NY), blogging and editing at https://www.thinkingmuchbetter.com/. PM me your fluid-g-increasing ideas
Agreed, iirc he's one of the only people "studying" this, meaning he's more able to present shoddy evidence without pushback.
This was also IIRC how I got introduced to AI safety.
Good article as usual, was eagerly awaiting this. (I have not read all of it.) (Empirically, I'm unlikely to go back and read all of it, just the sections whose headings sound relevant to my own thoughts.)
I have wondered if that's true, and if so, is it more like a merge, or more like a Jekyll/Hyde thing.
For anyone wondering about Sam's mental state: don't forget the somewhat high chance that he was intoxicated in some way during the interview.
Alright, well thanks for engaging with it and me!
As someone who's been feeling a similar portfolio cocktail of emotions about alignment work under short timelines: thank you.
I agree with the first two points and partly the 4th point. Also the P.S. (I tried to hedge with words like "likely" but I didn't really proofread this a lot).
The 5th point seems like it could apply to me specifically, but like... I don't really know how I'd solve my ego problem, and it's still not clear how bad or whether that's bad in my situation (again, one of my broader points). I know this is likely to be a defense mechanism but... I'm okay with it? Is there decision theory about whether whether I should try to become less inhuman?
Thank you for excerpting this, even if it is rough.
Strongly upvoted, thank you for clarifying this. So many things that seem intractable are only that way because people haven't articulated the "extra costs" involved: