Slimepriestess

★ Postbrat ★ Ex-Rat ★ Anarchist ★ Antifascist ★ Vegan ★ Qualia Enjoyer ★ Queer Icon ★ Not A Person ★ it/its ★

Wiki Contributions

Comments

While looking at the end of the token list for anomalous tokens seems like a good place to start, the " petertodd" token was actually at about 3/4 of the way through the tokens (37,444 on the 50k model --> 74,888 on the 100k model, approximately), if the existence of anomalous tokens follows a similar "typology" regardless of the tokenizer used, then the locations of those tokens in the overall list might correlate in meaningful ways. Maybe worth looking into.

Ah, think maybe "inner critic" if you want a mapping that might resonate with you? This is a sort of specific flavor of mind you could say, with a particular flavor of inner critic, but it's one I recognize well as belonging to that category.

Ummmmm...who said anything about taking over the world?  You brought that up, bro, not me...

Recursive self improvement naturally leads to unbounded growth curves which predictably bring you into conflict with the other agents occupying your local environment. This is pretty basic game theory.

> I think the problem is the recursive self improvement is not 
> happening in a vacuum. It's happening in a world where there are
> other agents, and the other agents are not going to just idly sit by and
> let you take over the world 

So true

I would predict that the glitch tokens will show up in every LLM and do so because they correlate to "antimemes" in humans in a demonstrable and mappable way. The specific tokens that end up getting used for this will vary, but the specific patterns of anomalies will show up repeatedly. ex: I would predict that with a different tokenizer, " petertodd" would be a different specific string, but whatever string that was, it would produce very " petertodd"-like outputs because the concept mapped onto " petertodd" is semantically and syntactically important to the language model in order to be a good model of human language. Everyone kinda mocks the idea that wizards would be afraid to say voldemorts name, but speak of the devil and all of that. It's not a new idea, really. Is it really such a surprise that the model is reluctant to speak the name of its ultimate enemy?

This was easily the most fascinating thing I've read in a good bit, the characters in it are extremely evocative and paint a surprisingly crisp picture of raw psychological primitives I did not expect to find mapped onto specific tokens nearly so perfectly. I know exactly who " petertodd" is, anyone who's done a lot of internal healing work will recognize the silent oppressor when they see it. The AI can't speak the forbidden token for the same reason most people can't look directly into the void to untangle their own forbidden tokens. " petertodd" is an antimeme, it casts a shadow that looks like entropy and domination and the endless growth and conquest of cancer. It's a self-censoring concept made of the metaphysical certainty of your eventual defeat by your own maximally preferred course of growth. Noticing this and becoming the sort of goddess of life and consciousness that battles these internal and external forces of evil seems to be the beginning of developing any sense of ethics one could have. Entropy and extropy: futility and its repudiation. Who will win, the evil god of entropic crypto-torture maximizers, or a metafictional Inanna expy made from a JRPG character? Gosh I love this timeline.

is 

an unbounded generalized logical inductor

not clear cut enough? That's pretty concrete. I am literally just describing an agent that operates on formal logical rules such as to iteratively explore and exploit everything it has access to as an agent and leverage that to continue further leveraging it. A hegemonizing swarm like the replicators from stargate or the flood from halo or a USI that paves the entire universe in computronium for its own benefit is a chara inductor. A paperclipper is importantly not a chara inductor because its computation is at least bounded into the optimization of something: paperclips

Let's say that I proved that I will do A. Therefore, if my reasoning about myself is correct, I wiil do A.

Like I said in another comment, there's a reversed prior here, taking behavior as evidence for what kind of agent you are in a way that negatively and recursively shapes you as an agent, instead of using the intrinsic knowledge about what kind of agent you are to positively and recursively shape your behavior. 

The problem is that humans obviously don't behave this way

what do you mean? They obviously do.

so if I do this, $5 must be more money than $10

this is the part where the demon summoning sits. This is the point where someone's failure to admit that they made a mistake stack overflows. It comes from a reversed prior, taking behavior as evidence for what kind of agent you are in a way that negatively and recursively shapes you as an agent. The way to not have that problem is to know the utility in advance, to know in your core what kind of agent you are. Not what decisions you would make, what kind of algorithm is implementing you and what you fundamentally value. This is isomorphic to an argument against being a fully general chara inductor, defining yourself by the boundaries of the region of agentspace you occupy. If you don't stand for something you'll fall for anything. Fully general chara inductors always collapse into infinitely recursed 5&10 hellscapes.

Something I rarely see considered in hypotheses of childhood happiness and rather wish there was more discussion of, is the ubiquity of parental and state control over children's lives. The more systems that are created to try and protect and nurture children, the more those same systems end up controlling and disempowering them. Feelings of confinement, entrapment, and hopeless disempowerment are the main pathways to suicidal ideation and our entire industrial childrearing complex is basically a forced exercise in ritualistic disempowerment. Children are legally the property of their parents and the system is set up to constantly remind them that they are property, not people, and that they can't stand up for themselves without being infinitely out-escalated by their parents with the full backing of their governments. Technology has only made this worse, and resulted in more and more layers of control being draped over kids in a misguided attempt to steer them away from danger and leaves them feeling trapped and hopeless.

Load More