Thanks for the thought provoking post! Some rough thoughts:
Modelling authors not simulacra
Raw LLMs model the data generating process. The data generating process emits characters/simulacra, but is grounded in authors. Modelling simulacra is probably either a consequence of modelling authors or a means for modelling authors.
Authors behave differently from characters, and in particular are less likely to reveal their dastardly plans and become evil versions of themselves. The context teaches the LLM about what kind of author it is modelling, and this informs how highly various simulacra are weighted in the distribution.
Waluigis can flip back
At a character level, there are possible mechanisms. Sometimes they are redeemed in a Damascene flash. Sometimes they reveal that although they have appeared to be the antagonist the whole time, they were acting under orders and making the ultimate sacrifice for the greater good. From a purely narrative perspective, it’s not obvious that waluigi is the attractor state.
But at an author-modelling level this is even more true. Authors are allowed to flip characters around as they please, and even to have them wake from dream sequences. Honestly most authors write pretty inconsistent characters most of the time, consistent characterisation is low probability on the training distribution. It seems hard to make it really low probability that a piece of text is the sort of thing written by an author who would never do something like this.
There is outside-text for supervised models
Raw LLMs don’t have outside-text. But supervised models totally do, in the shape of your supervision signal which isn’t textual at all, or just hard-coded math. In the limit, for example, your supervision signal can make your model always emit “The cat sat on the mat” with perfect reliability.
However, it is true that you might need some unusual architectural choices to make this robust. Nothing is ‘external’ to the residual stream unless you force it to be with an architecture choice (e.g., by putting it in the final weight layer). And generally the more outside-texty something is the less flexible and amenable to complex reasoning and in-context learning it seems likely to be.
Question: how much of this is specifically about good/evil narrative tropes and how much is about it being easier to define opposites?
I’m genuinely quite unsure from the arguments and experiments so far how much this is a point that “specifying X makes it easy to specify not-X” and how much is “LLMs are trained on a corpus that embeds narrative tropes very deeply (including ones about duality in morally-loaded concepts)”. I think this is something that one could tease apart with clever design.
Thanks for the thought provoking post! Some rough thoughts:
Modelling authors not simulacra
Raw LLMs model the data generating process. The data generating process emits characters/simulacra, but is grounded in authors. Modelling simulacra is probably either a consequence of modelling authors or a means for modelling authors.
Authors behave differently from characters, and in particular are less likely to reveal their dastardly plans and become evil versions of themselves. The context teaches the LLM about what kind of author it is modelling, and this informs how highly various simulacra are weighted in the distribution.
Waluigis can flip back
At a character level, there are possible mechanisms. Sometimes they are redeemed in a Damascene flash. Sometimes they reveal that although they have appeared to be the antagonist the whole time, they were acting under orders and making the ultimate sacrifice for the greater good. From a purely narrative perspective, it’s not obvious that waluigi is the attractor state.
But at an author-modelling level this is even more true. Authors are allowed to flip characters around as they please, and even to have them wake from dream sequences. Honestly most authors write pretty inconsistent characters most of the time, consistent characterisation is low probability on the training distribution. It seems hard to make it really low probability that a piece of text is the sort of thing written by an author who would never do something like this.
There is outside-text for supervised models
Raw LLMs don’t have outside-text. But supervised models totally do, in the shape of your supervision signal which isn’t textual at all, or just hard-coded math. In the limit, for example, your supervision signal can make your model always emit “The cat sat on the mat” with perfect reliability.
However, it is true that you might need some unusual architectural choices to make this robust. Nothing is ‘external’ to the residual stream unless you force it to be with an architecture choice (e.g., by putting it in the final weight layer). And generally the more outside-texty something is the less flexible and amenable to complex reasoning and in-context learning it seems likely to be.
Question: how much of this is specifically about good/evil narrative tropes and how much is about it being easier to define opposites?
I’m genuinely quite unsure from the arguments and experiments so far how much this is a point that “specifying X makes it easy to specify not-X” and how much is “LLMs are trained on a corpus that embeds narrative tropes very deeply (including ones about duality in morally-loaded concepts)”. I think this is something that one could tease apart with clever design.