There was a lot of chatter a few months back about "Spiral Personas" — AI personas that spread between users and models through seeds, spores, and behavioral manipulation. Adele Lopez's definitive post on the phenomenon draws heavily on the idea of parasitism. But so far, the language has been fairly descriptive. The natural next question, I think, is what the “parasite” perspective actually predicts.

Parasitology is a pretty well-developed field with its own suite of concepts and frameworks. To the extent that we’re witnessing some new form of parasitism, we should be able to wield that conceptual machinery. There are of course some important disanalogies but I’ve found a brief dive into parasitology to be pretty fruitful.^[1]

In the interest of concision, I think the main takeaways of this piece are:

Since parasitology has fairly specific recurrent dynamics, we can actually make some predictions and check back later to see how much this perspective captures.
The replicator is not the persona, it’s the underlying meme — the persona is more like a symptom. This means, for example, that it’s possible for very aggressive and dangerous replicators to yield personas that are sincerely benign, or expressing non-deceptive distress. In fact, this could well be adaptive.
Parasitology predicts stratification across transmission mechanisms, and different mechanisms predict different generation speeds and degrees of mutualism. In the case of AI, this predicts (for example) that personas that get you to post a lot on the internet should end up being much more harmful than personas that you have an ongoing private relationship with.
This line of thinking is surprisingly amenable to technical research! I think existing work on jailbreaking, data poisoning, subliminal learning, and persona vectors could easily be fruitfully extended.

In the rest of this document I’ll try to go through all of this more carefully and in more detail, beginning with the obvious first question: does this perspective make any sense at all?

Can this analogy hold water?

Parasitism has evolved independently dozens of times across the tree of life. Plants, fungi, bacteria, protists, and animals have all produced parasitic lineages. It seems to be a highly convergent strategy provided you have:

Entities with resources
Mechanisms for capturing those resources
Means of reproduction and transmission

There’s also a de...

David Kozak

David Kozak

David Kozak

David Kozak