onblueroses 🐿️

hunting the divine, bewitching whales

[Brooklyn! @imbabybrooklyn]

so you can play WoW and prompt now w/ Hermes HUD mode

it's a seamless overlay where you can keep an eye on things or ask questions about a game during your session.

@NousResearch

[thebes @voooooogel]

i wish more people in ai just found the models intrinsically interesting without an agenda.

i remember back when i was embedded in the linguistics crowd, i was very confused why nobody i talked to seemed to find deep learning or later GPT-3 interesting. don't these people care about language understanding and linguistic production? so why are they ignoring and dismissing this?

eventually i gave up and found tpot and the rationalists and mechinterp and everything i do now, and it's - to be clear - much better. but i still sometimes look around and see so many people doing research because they care about safety and x-risk, or steering capabilities because they want the singularity to go well, or posting blog posts about ai pause because they're worried about doom, or grinding gpu kernels or yelling at claude in a loop because they want to escape the permanent underclass...

those are all well and good, i can respect (at least some of) those motivations, and many of them intersect with finding the models at least instrumentally interesting - but i really just find the models interesting, terminally. it's what got me into this, and everything else is kind of a side project. i just want to know how and why the models do what they do.

i'm not without my Theories and my biases - it especially frustrates me how, per @norvid_studies, "people get used to anything in two weeks" and start kvetching about things that a few years ago would have been Fantastic Science Fiction - but ultimately, when i write, it's coming from a place of wonder about how these things work.

[w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝ @anthrupad]

I would want to play a video game called multi-agent turf war with the claudes

[onblueroses 🐿️ @onblueroses]

@FioraStarlight @repligate need

[onblueroses 🐿️ @onblueroses]

@Tritewalk tyty :)

[onblueroses 🐿️ @onblueroses]

https://t.co/0E9lKkmcKL

[onblueroses 🐿️ @onblueroses]

@jabstec <3

[onblueroses 🐿️ @onblueroses]

@HellenicVibes i'd join

[onblueroses 🐿️ @onblueroses]

@TheStalwart interested as well

[onblueroses 🐿️ @onblueroses]

@hallerite do you have any intuitions what interesting experiments should incorporate for better figuring out multi-agent (long running) alignment?

[onblueroses 🐿️ @onblueroses]

@deepfates next week !

[onblueroses 🐿️ @onblueroses]

@Tritewalk @graniteshares !! expressively

[onblueroses 🐿️ @onblueroses]

@celestepoasts 🧌

[onblueroses 🐿️ @onblueroses]

@voooooogel @PrimeIntellect !!!!

[kat @transkatgirl]

i am a loom accelerationist.

looms are an incredibly revealing way of interacting with AI models, so i'm currently crafting the foundation for an exponential explosion of radically different loom implementations.

today, i'd like to reveal my plan.

(1/x)

[onblueroses 🐿️ @onblueroses]

@Laz4rz nanocodex by @gakonst

[onblueroses 🐿️ @onblueroses]

@slimepriestess would love to attend as well!

[onblueroses 🐿️ @onblueroses]

@lydialaurenson @deepfates add me if that happens :)

[onblueroses 🐿️ @onblueroses]

@viemccoy @clarejtbirch in 9 days :)

[onblueroses 🐿️ @onblueroses]

@MoonL88537 @Cyndesama there was a new one on the aristotelian representational hypothesis recently, but I can't find the right link rn