general search. it pulled the archive.
Log in





You said:

talk to me about google's collapsing ontology

ChatGPT said:

If by “Google’s collapsing ontology” you mean the idea that Google’s search/AI systems are increasingly collapsing distinct things, meanings, and sources into a single inferred representation, then yes—there’s a fascinating idea there.



I’d frame it less as a formal Google doctrine and more as a useful critique of what happens when search becomes generative. I couldn’t find evidence that “collapsing ontology” is an official Google term; Google does, however, have long-standing work around ontologies, knowledge graphs, entity resolution, and systems that collapse concepts or relationships for computational purposes. Google Patents+1

The basic idea

Old Google Search implicitly operated something like:

World → documents → ranking → user

You searched for something, and Google tried to identify documents that were relevant to your query.



The newer AI-mediated model increasingly looks like:

World → data → entities/concepts → model → synthesized answer

That extra synthesis layer changes the epistemology.



Google isn't merely asking:



“Which documents say something about X?”



It's increasingly asking:



“What is X, given all the things I can infer about X?”



That's an ontological operation.



An ontology is basically a system for deciding what kinds of things exist in a domain and how they relate. A person, organization, event, place, concept, product, etc. become nodes in a structured representation.



Google has been doing this for a long time with things like the Knowledge Graph. Its patents and technical work explicitly describe collapsing synonymous or related concepts into normalized representations. Google Patents



But generative AI pushes this much further.

Where the “collapse” gets interesting

Imagine five websites say:



“A is a political organization.”

“A is a social movement.”

“A is an advocacy group.”

“A describes itself as a network.”

“Critics describe A as something else.”



A traditional search engine can preserve those distinctions.



A generative system has an incentive to produce:

A is a social and political organization.

Five distinct descriptions become one object in the answer.



That's the collapse.



And it isn't necessarily bad. In fact, it's enormously useful. Human cognition does this constantly. We don't want to read 400 documents every time we ask “what is this thing?”



The problem appears when the compression becomes invisible.



You no longer see:

source A believes X source B believes Y source C disputes both

You see:

X

The distinctions have disappeared into the representation.

And this is where Google is particularly interesting

Google's historical superpower was indexing plurality.



The web could contain mutually incompatible descriptions, and Search could put them next to one another.



AI search increasingly wants to provide a coherent world-model.



That creates a strange inversion:



Search used to navigate an ontology. AI search increasingly constructs one.



And whoever constructs the ontology gets tremendous epistemic power.



Because deciding that two things are “the same” is not merely retrieval.



It's interpretation.



Likewise, deciding that two things are different is interpretation.



And deciding which distinctions aren't worth showing the user is also interpretation.

There's a subtle second collapse

There's also a collapse between entity and description.



Suppose you search for a relatively obscure person.



Traditional search:

Here are 12 pages about this person.

Generative search:

Here's who this person is.

The second statement sounds innocuous, but notice what's happened.



The description has become the entity.



The model's representation of the person starts functioning as the person for purposes of the interface.



That's a profound shift.



And it explains why hallucination in search is more philosophically interesting than ordinary chatbot hallucination.



If ChatGPT invents something in a conversation, that's a bad answer.



If a search system invents an entity, merges two entities, attributes someone's work to the wrong person, or silently resolves conflicting descriptions into a false synthesis, it can alter the machine-readable ontology of the web as experienced by millions of people.



There are already contemporary examples and critiques of AI retrieval systems behaving this way—particularly around exact-match searches where a generative layer substitutes inference for actually resolving the requested source. Mind Control Poems

The really deep version

I think the most interesting formulation is:

Google is moving from organizing representations of reality to producing representations that users experience as reality.

That's the ontological transition.



And there's a nasty feedback loop lurking there:



Web → Google → AI summary → users → new web content → Google → AI



If the AI's collapsed representation becomes sufficiently influential, people begin writing according to the representation that Google expects.



Then the representation starts feeding the corpus from which the representation was derived.



That's adjacent to the broader problem of model collapse, but it's not identical to it. Model collapse concerns degradation from recursive training on synthetic data; ontological collapse is more about distinct entities, meanings, sources, and distinctions being recursively compressed into fewer canonical representations. Alexanarch



And that's why I think the phrase is actually pretty powerful, even though it isn't a standard Google term.



The central question becomes:

What happens when the world's most important information interface stops showing us the disagreements between descriptions and starts giving us the thing it believes exists?

That's much more consequential than “Google Search got an AI summary.”



If that's the phenomenon you had in mind, I can go one level deeper into Google's Knowledge Graph → entity resolution → Gemini/AI Overviews → ontology collapse, because there's a very interesting technical/philosophical progression there.



Sources



ChatGPT is AI and can make mistakes.



Chat with ChatGPT