Very off topic: The only plausible reason I’ve heard to be “nice” to LLMs/virtual assistants etc. is if you are being observed by a child or someone else impressionable. This is to model good behaviour if/when they ask someone a question or for help. But also you shouldn’t be using those things anyhoo.

yeah filing this under my "ok so you know you can just have kinks, right? like you don't need to intellectually justify your kink. Have you seen a therapist?" folder

double check that your rubbers didn’t get punctured.

Extra wrinkly*, for your partner’s pleasure

106 comments

only 7 top level comments

Thank you lord for this feast you have blessed me with.

His LinkedIn has no background in tech beyond serving on the board of google health. He’s essentially just some guy!

I don’t recognise this ABBA song, must be a deep cut (jk)

??? Zack is a “I think you should leave” character

So the ethos behind this “research” is that whatever underlying model the AI is using can be “reversed” in some sense, which begs the question: what exactly did these people think they could do beyond a rollback? That they could beg the AI to stop being mean or something?

They were probably inspired by the blanka creation scene from the street fighter movie where they brainwash some guy by showing him video clips of bad stuff and then switch it to showing good stuff.

Yeah, that's where I'm at. I don't think this is Yud doing HPMOR and trying to rope randos into rationality. Well, maybe he's trying to rope the non-rat glowfic enjoyers, idk. In any case, this is Yud playing with a pal and having fun, I guess? Take that as you will.

is this written by a grown man or a 14 year old emo kid

yes

(the MC is jughead from Riverdale lel)

They originally wanted a place that had a motte (and bailey).

Broke: contemporary dentistry

Still broke: putting GM bacteria in your mouth to prevent cavities

Woke: examining your teeth for cavities before and after licking interesting objects found in nature and getting bonus nootropics out of it