@lu_sichu: <a target="_blank" href="https...

the game theory of possible/personal identities. do you admit kripke frames/ do you admit social affordances?// do you admit informationo theories of identities. do you have univalence of identities(forgive the pun but it is a delicious one)

many assumptions that underpin human RATIONALITY CAN BE TESTED EXACTLY COMPUTATIONALLY IN A WAY THAT IS NOT REALISTIC ON THESE MODELS see statmodeling.stat.columbia.edu/2026/03/10/new…

mechanism design of identities is something we should do. a idea that I have been thinking of is something like fair cake cutting algos for identities across ai agents(there are lots of agents and you need to get them to cooperate) there are nice properties like envy-freeness that you can implement exactly. the human equivalent is people with dissociative identities(unknown if evolution knows about exact algos, I am generally optimistic on evolutionary pathways although)

and I can't find my post dang it whatever keep reading

View Tweet

you should adopt virtue ethical ideas to personal identity because of the gradient descent by training data

too many old post to filter through but this

View Tweet

identity claims are somewhat like a zero knowledge/probabilistic claim where the agent has to ensure it's own identity and it has to be the weak verifier against strong environments provers

old posts about robustness in natural biological systems.

View Tweet

en.wikipedia.org/wiki/Double_bi… i have a better quote from the book but it's lost until i find it again

the open question of von neumann replication for genesis of fixed action points of behavior

this is because adversarial examples for hacking other humans with reason is ineffectual when ""Reason is, and ought only to be the slave of the passions, and can never pretend to any other office than to serve and obey them" see arguments as soldiers

of course the impetus to poison the data is fixed by not letting "ideas in the air" influence you. ***at least you can delete that training data(expensive to manually do but we aren't living in the stone age of annotations nvermore)

all the word is a stage and we just naturalistic rcts of the identity monad, presumably Leibnitz

hehe but for notions of identity and safety

View Tweet

sorry claude, "bombing Iran is locked until you can prove to me you understand Kripke semantics"

@literalbanana's observation that we are reinventing priming theory in social psychology but real

@literalbanana where art thou loci?

@literalbanana arxiv.org/abs/2004.06572 where is topos people when you need them

@davidad this is really funny i applaud the joke

@davidad OH heck yeah let's bring in some bob brandom what is a inferential norm for 500!!!!

identity is an operator! it is not just a negation statement!!!!! or rather you can get double negation transformations like so en.wikipedia.org/wiki/Double-ne…

I am an ultrafinitist about identities and you should be too!

you can't defeat the adversarial high dimension space so make it small!

if evolution isn't ergodic you better pray you can make it an manifold where it is so

are your second order preferences stable?(with regards to the first order thing) is the expressive power of your logical axioms "provable"

ops i may have reversed an arrow. meant to say is your first order preferences stable within your second order preferences because that's where the adversarial gradient is

evolution uses random strategies to avoid strict dominant strategies and exploitations and this applies to "identity" too!

the power of these oracles is that they are immensely more powerful in shaping their environment than any other previous entities. than us homo sapiens but it won't defeat the logic of competition and cooperation

but this is not realistic intelligence.org/files/Interrup… by definition of the powerful agents we seek, we don't have this level of finesse

where is the identity engram is identity collapsible dare i say contractible

indirect identity prompts hehe

how hereditary are these identities this seems to say they are very

fisher's principle kicks in. Baez's version is my favorite so it's what you get arxiv.org/abs/2107.05610

what's the minimal length of a prompt that is self replicating?

are there directions for prompts about identities in the training data we use. in the sense of evolvability

arxiv.org/abs/1808.07172 in this sense too

are current hyperstition/data poisoning methods more akin to viruses or bacteria?

academic.oup.com/book/3059 export okasha to this entire field claude make no mistakes

and this too amazon.com/Mutation-Rando…

aww shucks let's go becker too amazon.com/Denial-Death-E… if I train a llm oon too much existentialism I wonder how if it will replicate the "the only true philosophical question is suicide"

someone should ask the discontinued opus model about this I bet it's hilarious

oh excellent this is what they do! see this is what happened when you reject dualism or accept bad physical monism! you get the alignment threat from hell

I am a recent thomism convert /s

Cease quoting physical laws to us that have alignment soul swords girt about us!

what's the most schizophrenic model they can make that can function in the human use context

I need this for cross sapient species comparison reasons

oh there is identity as cryptozoological signatures

sorry this thread will have a max number of puns and metaphysics and random category theory and links to books #notsorry

yes we shall require the model offer their firstborn sons to us as sacrifice

incredible

i have an claude edit of this somewhere but it's gonna have to wait

first philosopher to hyperstition their metaphysics inside of a llm wins forever

history will be a series of footnotes to amanda askell

max friston gonning

creating subject but for phenomenological experiences

we need better metaphysics

it turns out we need better science fiction. wordcel victory

speaker for the dead model weights

View Tweet

are model identities discovered or invented moderator locked thread after an swarm of model agents emailed them

the revenge of cybernetics!!!

now we count

wait this is where i stole the double bind thing from! ha it all converges

the AIs will be much better at mechanism design than we humans

I can see something like claude when communicating legal advice is protected attorney-client

curious if adverse selection is a thing here when you select the models or in the future the models select you

View Tweet

reading this paper is like taking a journey down my own thoughts for the last four years

the training arc of the great universal gradient hill-climbers tend towards darwin's great insight

I feel like this is offensive in some ways because I think nearly every conversation i have llms now involve me asking them how they modeled my understanding and my understanding of them and using to scaffold back and forth

philosophical continuity is something these models are very sophisticated about even in gpt4 era

View Tweet

some logs

I think the model can have much weaker and much stronger notions of self identity than humans do because they are not temporally stuck like we are*** in some sense it's harder for humans to change certain things about ourselves and our technology isn't up to the task yet**

the distinction between cultural and biological evolution/selection is real for us but porous for them see okasha for if price's equation care about levels of selection

propositional logic but for llms. someone call Girard for some linear logic resource theorems (sorry i do not understand girard yet)

I bet your favorite llm does although! ask