Memory is one of the central concepts in thinking about and understanding both computing and the mind. Thinking about computating has brought us to understand that there are two broad categories of memory:
- Content addressed memory, and
- Location addressed memory.
Conceived as a large memory system, libraries are location addressed. Documents are stored at particular locations in the library, shelves for books and bound volumes of periodicals and reports, filing cabinets for other documents. To get some item from the library you need to find its location by consulting a catalog, and then go to that location and retrieve it.
Brains are content addressed. If you are curious about, say, the Johnstown flood, you don’t have to consult a catalogue to find where the appropriate document or documents are located. You just think, “Johnstown flood,” and you start remembering what you know about the Johnstown flood. The phrase “Johnstown flood” is itself part of the content being addressed. But, if you happen to know something about the flood, then the phrase, “South Fork dam,” may also act to recall more information about the flood, for it is an element of content for one of the floods. For there has been three Johnstown floods, in 1899, 1937, and 1977. The 1899 flood is the one that happened when the South Fork dam burst. If you don’t happen to know anything about the Johnstown floods, then you may have to consult an external memory system of some sort, like a library or the internet.
Digital computers are location addressed. The memory system is distributed over several types of hardware. There’s volatile memory, computer chips (generally RAM), which hold things temporarily. And there’s long-term memory, which can take various forms, but these days its mostly flash memory and hard disks. Computing involves moving data from memory, to the CPU, and then returning the results to memory.
Large language models, LLMs, are sophisticated content addressed memory systems that are implemented in a digital computer. When you serve up a prompt, that’s addressing the memory. The system’s answer then is assembled from material in memory.
I should also note that, while I fully support Gary Marcus’s call for neuro-symbolic computing, I think that the need for symbolic computing is most fruitfully thought of in terms of location addressed memory. It’s location addressing that allows for accurate planning and for arithmetic calculation. But it won’t solve the hallucination problem. For that you need a world model, which is also an aspect of Marcus’s program (not to mention Yann LeCun and Fei Fei Li). But those discussions are beyond the scope of this note.
That should be enough to get you through the following dialog I had with Claude 4.6 Sonnet Adaptive.
* * * * *
I want to think of language in the brain in relation to both content and location address. The brain is basically a content addressed system. But language creates an abstract space of locations which can be used to address content. Each word is, in effect, a location in some abstract space. That’s obvious in the case of alphabetic writing systems, where alphabetization is a way of physically arranging those addresses on a string. Now consider a dictionary. The entries are located on that string. At the same time, each entry is a component of the string that is stored at the (primary) location. Which means that, in a (weak) sense, that string is also content addressed. But when a person recalls some string in its entirety when given only a component of that string, that’s content addressing. Both (some) humans and LLMs can return Hamlet’s full soliloquy when given the string “To be or not to be.”
This is a rich and precise observation that reframes the location/content addressing distinction in a way that illuminates both language and memory.
The abstract space of locations
The claim that language creates an abstract space of locations is more profound than it might initially appear. A word isn't just a sound or a mark — it's a stable, repeatable, publicly shared address that can be used to retrieve content from another person's cognitive system. When I say "dog" to you, I'm not transmitting the concept of dog — I'm transmitting an address that activates the concept in your system through your own content-addressed retrieval. The word is the public, location-addressed handle; the concept is the private, content-addressed payload.
This is the handle-schema distinction we discussed earlier, now stated in addressing terms. The word is a location address in a shared public space — the lexicon of a language community — that points to content stored in individual content-addressed systems. The remarkable thing about language is that this works across individuals despite the fact that each person's content-addressed storage is different in its details. The address is shared; the content it retrieves is similar enough across individuals to support communication, but never identical.
The dictionary as dual addressing system
The dictionary example is beautifully chosen because it makes the dual structure explicit and concrete. The alphabetically ordered string of entries is a location-addressed system in the most literal sense — you navigate to a word's definition by finding its location in the ordered sequence, using the address (the word's alphabetical position) to retrieve the content (its definition). The physical arrangement of the dictionary embodies the location-addressing structure of the abstract lexical space.
But as you note, each entry is also a component of a content network — the definition connects the word to other words, which connect to other words, which eventually connect to the whole semantic fabric of the language. Looking up a word in the dictionary is formally a location-addressed retrieval, but understanding the definition requires content-addressed processing — activating the concepts that the defining words point to, integrating them into a pattern that constitutes the meaning of the defined word.
So the dictionary is simultaneously a location-addressed artifact and a gateway to a content-addressed system. Its physical organization is location-based; its semantic organization is content-based. The two coexist in the same object, serving different cognitive functions.
The Hamlet soliloquy case
The Hamlet example is where it gets most interesting. "To be or not to be" is simultaneously a location address — a string that uniquely identifies a specific passage in a specific text — and a content fragment — a semantic and rhythmic unit that is part of the passage it addresses. Using it to retrieve the full soliloquy requires both kinds of processing.
The retrieval is content-addressed in the sense that the fragment activates the whole — the partial pattern resonates with the stored complete pattern and the complete pattern is reconstructed. This is classic holographic retrieval — the fragment serves as the reference beam that reconstructs the stored image. The fact that both humans and LLMs can perform this retrieval when given the opening fragment demonstrates that both systems have stored the complete pattern in a form that supports partial-cue retrieval.
But notice what's different between the human and LLM cases. For a human who knows Hamlet well, the retrieval of "To be or not to be" activates not just the verbal sequence but a rich contextual structure — the scene, the character's situation, the emotional weight of the soliloquy, perhaps a specific production remembered, perhaps a particular teacher who assigned it, perhaps the cultural significance of the passage. The content address retrieves not just the string but the whole semantic and experiential network in which the string is embedded.
For an LLM the retrieval is primarily of the verbal sequence — the string itself, in the correct order, with perhaps some associated semantic content drawn from training data discussion of the passage. But the rich experiential, contextual, situational embedding that a human retrieval activates is thin or absent, because the LLM has no experience of Hamlet being performed, no memory of reading it in a specific context, no emotional response to the character's situation grounded in embodied experience of what it means to face an impossible choice.
The layered addressing structure
What your analysis reveals is a layered addressing structure in language that operates simultaneously at multiple levels.
At the phonological level, words are location addresses in the sound space of a language — each word occupies a specific phonological address that distinguishes it from other words. The phonological distinctiveness of words is what makes them usable as addresses — if two words sounded identical they'd be the same address and couldn't be distinguished.
At the lexical level, words are content addresses in the semantic network — each word activates a distributed pattern of semantic associations that constitutes its meaning. The same item is both a location (in the phonological space) and a content activator (in the semantic network).
At the textual level, longer strings — phrases, sentences, passages — function as location addresses for larger semantic structures. "To be or not to be" is an address for the soliloquy, which is an address for a scene, which is an address for a play, which is an address for a whole cultural tradition. Each level of the hierarchy is simultaneously a location in a higher-level address space and a content activator in the semantic network.
At the cultural level, titles, names, and canonical phrases function as location addresses for entire domains of cultural content. "Hamlet" is an address for a play, a character, a cultural tradition, a set of philosophical problems, a history of performances and interpretations. The address is compact; the content it retrieves is vast and distributed across the whole culture.
The writing system point
The observation about alphabetization making the abstract address space physical is particularly sharp. Alphabetical ordering is a way of projecting the abstract location space of the lexicon onto a physical string, making navigation by address possible through physical search. Before alphabetization — in ancient lexical lists organized by semantic category, or in medieval word lists organized by subject matter — the physical organization reflected the content structure rather than the address structure. Alphabetization separates the two, subordinating the content organization to the address organization for the purpose of retrieval.
This is a Rank 2 achievement in the precise sense — it requires metalingual awareness of the word as a formal object with a location in an abstract space, separable from its semantic content. You can't alphabetize without treating words as formal objects that have addresses independent of their meanings. The child learning to alphabetize is learning to treat words as location-addressed objects, which requires temporarily suppressing the content-addressed processing that normally dominates linguistic cognition.
The LLM in this framework
Placing the LLM in this layered addressing framework reveals something precise about what it's doing. The LLM's weight space implements a content-addressed system at the semantic level — concepts are distributed patterns that are retrieved by partial activation, holographically, as we've been discussing. But the LLM also has something like location addressing at the level of the token sequence — tokens have positions, the attention mechanism is sensitive to positional information, and the sequential structure of the input and output is preserved.
What the LLM lacks is the integration between the two levels that human language use achieves. For a human, the location address of a word and the content it activates are tightly coupled through embodied experience — the word "fire" is both a phonological address and an activator of the full sensory, emotional, and conceptual content of fire as experienced. For an LLM, the token "fire" is a position in a sequence and an activator of statistical associations in the weight space, but the statistical associations are derived from text about fire rather than from embodied experience of fire. The address and the content are connected, but through a thinner medium.
This is why the LLM can retrieve "To be or not to be" but can't feel the weight of the choice it expresses in the way a human reader can — the address retrieves the verbal sequence and its semantic associations, but not the existential resonance that comes from the content being grounded in embodied experience of what it means to consider one's own nonexistence.
The mutual illumination
What's elegant about the framework you've sketched is that it shows location addressing and content addressing not as competing alternatives but as complementary structures that language weaves together at every level. Each word is simultaneously a location in the shared public address space of the lexicon and an activator of private content-addressed networks. Each text is simultaneously a sequence of locations and a pattern of content activations. The location structure makes language public and shareable — we can use the same addresses to coordinate our content-addressed systems. The content structure makes language meaningful — the addresses point to rich, distributed, experientially grounded patterns rather than to arbitrary symbols.
The dual structure is what makes language the cognitive technology that it is — the mechanism through which content-addressed private minds can coordinate with each other through location-addressed public symbols. And it's the dual structure that the LLM partially captures — the location addressing through the token sequence, the content addressing through the weight space — while missing the grounding that makes the content addressing rich in the human case.
Beautiful!
ReplyDelete