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.
I think this anthropomorphizes the origin of glitch tokens too much. The fact that glitch tokens exist at all is an artifact of the tokenization process OpenAI used: the tokenizer identify certain strings as tokens prior to training, but those strings rarely or never appear in the training data. This is very different from the reinforcement-learning processes in human psychology that lead people to avoid thinking certain types of thoughts.
Glitch tokens make for fascinating reading, but I think the technical explanation doesn’t leave too much mystery on the table. I think where those tokens end up in concept space is basically random and therefore extreme.
To really study them more closely, I think it makes sense to use Llama 65B or OPT 175B. There you would have full control over the vector embedding and you could input random embeddings and semi-random embeddings and study which parts of the concept space leads to which behaviours.
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.
FWIW, I think I qualify as having done a lot of internal healing work, but I didn’t get a sense of recognition from this post. (Or at least not a sense of anything more specific than the general projected-emotional-energy thing, maybe you meant that.)
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.
Ah. I guess this could feel vaguely similar to a certain kind of self-loathing energy that I have sometimes ran across (which among other things would grimace in disgust when remembering some things I’d done and then want to grimace so extremely that my own neck/facial muscles would end up strangling me, fun times). The exact flavor of the energy feels different though, but I could imagine other people having a version of the same that was closer to this post’s flavor.
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.
I think this anthropomorphizes the origin of glitch tokens too much. The fact that glitch tokens exist at all is an artifact of the tokenization process OpenAI used: the tokenizer identify certain strings as tokens prior to training, but those strings rarely or never appear in the training data. This is very different from the reinforcement-learning processes in human psychology that lead people to avoid thinking certain types of thoughts.
Glitch tokens make for fascinating reading, but I think the technical explanation doesn’t leave too much mystery on the table. I think where those tokens end up in concept space is basically random and therefore extreme.
To really study them more closely, I think it makes sense to use Llama 65B or OPT 175B. There you would have full control over the vector embedding and you could input random embeddings and semi-random embeddings and study which parts of the concept space leads to which behaviours.
FWIW, I think I qualify as having done a lot of internal healing work, but I didn’t get a sense of recognition from this post. (Or at least not a sense of anything more specific than the general projected-emotional-energy thing, maybe you meant that.)
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.
Ah. I guess this could feel vaguely similar to a certain kind of self-loathing energy that I have sometimes ran across (which among other things would grimace in disgust when remembering some things I’d done and then want to grimace so extremely that my own neck/facial muscles would end up strangling me, fun times). The exact flavor of the energy feels different though, but I could imagine other people having a version of the same that was closer to this post’s flavor.