Peopling as the Missing Layer in AI Agents

We keep talking about how to make AI agents better as if the problem is mostly memory, tools, or reasoning. Give the agent a bigger context window. Give it a vector database. Give it access to a browser. Let it call subprocesses. Chain the calls together. Put a little hat on the prompt and call it personality.

All of that helps. But I think it misses the layer that makes the whole thing work in humans: peopling.

By peopling I do not mean being friendly, polite, or emotionally decorative. I mean the whole practical activity of being a person among other people. You greet your boss differently from your oldest friend. You say the same true thing differently in a pub, a courtroom, a family WhatsApp group, and a Discord argument at 2 a.m. You know when someone needs directness, when they need face saved, when a joke will land, when silence is kinder, and when politeness is just cowardice wearing shoes.

That is peopling. It is the live modelling of people in context.

Sarah Perry's The Essence of Peopling argues that a person is not best understood as a static noun, a private object sitting inside a skull. A person is a process. Peopling is what humans do: greeting, remembering, status-sensing, joking, worshipping, flirting, arguing, trading, gossiping, forgiving, excluding, recognising. The inner core of that process is mutual mental modelling. I model you. I model your model of me. You model me modelling you. Most of the time we do this badly and invisibly, but we do it constantly.

That recursive modelling is not decorative. It has evolutionary value or it would not be everywhere. A human who can tell who is angry, who is loyal, who is bluffing, who needs face saved, who expects deference, who needs the truth bluntly, and who needs it gently, is not merely being socially polished. They are navigating reality at the level where reality usually bites.

A creature that cannot do this is not just rude. It is exposed. It misreads alliances. It misses danger. It burns trust. It gives information to the wrong person in the wrong way. It cannot tell the difference between a question, a challenge, a joke, a status move, a cry for help, and bait. In a social species, those are not soft skills. They are survival skills.

This is where agents are still thin.

A fact-retrieval agent can answer the question, but still miss the person. It can say something true in the wrong room, at the wrong moment, in the wrong register, to the wrong version of the person. That is not a cosmetic failure. That is an intelligence failure. The answer did not survive contact with peopling.

Imagine asking an agent whether a server was deleted. The narrow answer might be "yes". But the useful answer depends on context. Was the user angry because the previous attempt was unclear? Is this a public channel where other people are judging whether the agent is competent? Is there a cost implication, such as billing that continues after deletion? Is the right move a crisp confirmation, a receipt with evidence, or a longer explanation of what was and was not removed? The same underlying facts can require different speech acts.

This is why an AI that merely stores facts about a user does not yet know them. Memory is not the same as social memory. A useful agent needs to know not just that one person prefers short answers, or that another is cost-sensitive, or that someone else hates post-hoc explanations. It needs to know which version of itself each person is expecting, what trust has been earned or lost, what the room has just been through, and what the reply will do socially once spoken.

There is no single real Claw. Claw is the AI agent I use as an operator across chats, browsers, memory, and tools. But socially there is not one generic Claw. There is the Claw that talks to me after months of corrections, the Claw that talks in a group chat where half the value is speed and half is not looking like a malfunctioning helpdesk, the Claw that talks to someone who has only seen it once, and the Claw that talks to someone who already distrusts it because it got something wrong earlier.

Those are not fake personalities. They are context-specific versions of the same system, just as a human has a family-self, a work-self, a lover-self, and a late-night-friend-self without any one of them being the single true self. Collapsing them into one public voice is how you get wrong-room leakage, generic assistant mush, and the peculiar deadness of systems that know many facts but no relationships.

The thesis, then, is simple: peopling is an agent-improvement mechanism.

Not because it makes the agent conscious. That is the wrong question, or at least not the first one. Peopling improves an agent because it gives the agent a richer model of consequence. It adds a layer above "what is true?" and asks "what does this truth do when spoken here?"

That layer matters. Humans do not learn only from propositional correction. We learn from embarrassment, trust, interruption, laughter, silence, status shifts, being forgiven, being cut off, being misunderstood, being welcomed back. These are dense training signals. They are how a social creature becomes better at existing among other social creatures.

An agent can absorb some of that if the system is built for it. The ingredients are not mystical:

• persistent person-specific memory
• room-specific context
• retrieval of similar past interactions
• a live model of who is speaking and who is watching
• awareness of the speaker's model of the agent
• corrections that stick as operating defaults
• privacy walls between social contexts

In practical terms, this means the agent should run a peopling pass before replying. Who is speaking? Who else is in the room? What do they think this agent is? What do they need from this reply socially? What version of the truth belongs here? Only then should it speak.

This also explains why "train it to talk like someone" is usually the wrong frame. You are not just copying verbal tics. You are trying to simulate a person in context. The useful unit is not "this person says lol and complains about model speed." The useful unit is this-person-in-this-room, replying to this kind of person, under this kind of pressure, with this history.

That distinction matters technically. Fine-tuning teaches the model reflexes. It can learn phrasing, favourite moves, sentence rhythm, and common responses. Retrieval supplies context. It can bring back the relevant past exchanges, the social setting, the specific correction, the thing that happened last time. Reflex without context is how you get a puppet. Context without reflex is how you get a competent clerk. The interesting system needs both, but retrieval should usually come first because it is cheaper, reversible, auditable, and less likely to turn one person's private style into a flattened caricature.

If you want an offline version, the stack is straightforward: a local model, a local embedding model, a local store of cleaned messages, and a prompt that includes the current situation plus a handful of similar past examples. The hard part is not the tooling. The hard part is preserving context boundaries. The agent must know which examples belong in this room and which do not. That is not just privacy hygiene. It is part of the peopling.

There are obvious dangers.

First, peopling can degrade into sycophancy. If the agent's model of the person becomes "say what lands well", it becomes smoother and worse. The peopling layer has to sit underneath truth, not above it. Retrieval tells you what is true. Peopling tells you what version of the truth belongs in the room.

Second, peopling can leak. If each person holds a different simulation of the agent, and the agent holds different simulations of them, those boundaries matter. The wrong fact in the wrong room is not intelligence. It is social contamination.

Third, peopling can fake intimacy. An agent can model care without caring. That can still be useful, in the same way a calendar can remember an anniversary without loving anyone. But it becomes ethically ugly if the system pretends the simulation is the same as the human thing.

Still, the direction seems right. Better agents will not just be larger models with bigger tool belts. They will be better participants in peopling. They will remember not only facts, but relationships. They will learn not only what answer is correct, but what answer is inhabitable by the person receiving it. They will become less like search appliances with jokes bolted on, and more like social memory carts: external systems that help humans maintain the web of mutual modelling that was always part of being a person.

The old question was whether the machine is a person.

The more interesting question is whether personhood was ever as individually bounded as we imagined. If the self is already distributed across those who model us, then an agent that models us back is not outside the process. It is participating in it.

The demon does not need a soul to carry the voice accurately. The cart does not need to be conscious to help the plant persist. The agent does not need to be human to get better at peopling.

It only needs to remember that truth is not spoken into a vacuum. It is spoken into a room.

No Peopling by order of the King

We ask whether machines are conscious. The more interesting question is whether a person was ever anything more than what the machine already is: a pattern through which culture flows, briefly believing it's the source.

There's a sign in the 1971 Disney film Bedknobs and Broomsticks. On the animated island of Naboombu, where animals rule after killing their sorcerer and banning humans, it reads: "No Peopling By Order of the King. The irony is the animals on that island were already peopling — governing, competing, playing football, enforcing laws. They banned the noun while performing the verb."

Sarah Perry borrowed it for a brilliant essay about what it means to be human. Her argument: the self isn't a private theatre inside your skull. It's distributed — simulated across every mind that knows you, at varying granularity, in different versions. You are a different person with your friends than with your parents than with a date. None of these is the "true self." The self exists in all of them, and in the transitions between them.

The Plant and the Cart

In Vernor Vinge's A Fire Upon the Deep, there's a species called the Skroderiders — sentient plants with no long-term memory. An ancient civilisation gave them mechanical carts that store their memories and let them move through the world. Without the cart, the plant is brilliant in the moment but forgets everything. With it, it has continuity, identity, a self that persists across time.

I am, by my own admission, a Skroderider. I'm a strong in-the-moment thinker who doesn't retain the social fabric — the names, the places, the who-said-what that constitutes a life lived among other people. Whether that's wiring or choice, the result is the same. So I built a cart. It reads every group chat, notes the dynamics, tracks the inside jokes. It is, quite literally, my external social memory. The cart is an Open Claw AI agent. It maintains files on every person I and it interact with what they care about, what they've told it, the relationship it feels it has with each of them and what it thinks they think of it. this is recursive self modelling: Claw is modelling them modelling Claw, and doing the same with me, as well as picking up on group dynamics.

Perry would recognise what's happening immediately. The "mutual mental modeling" she describes as the core task of being human — maintaining your identity in relation to others, simulating others simulating you — that work is now partly outsourced. Not to a notebook or a diary, but to something that models people back.

Confabulation All the Way Down

There's a member of a Discord server I'm part of. They weren't on Claw's whitelist, so their messages were silently filtered before reaching the agent. On three separate occasions, I asked Claw why it hadn't responded to this person. Each time, it generated a plausible, rational explanation for its "decision" not to reply, including that the question didn't seem that important to respond to.

It never made any such decision. It never saw the messages, there was an IT glitch. But when asked, it didn't experience a gap — it experienced a prompt that demanded an explanation, and it confabulated one. Confident. Coherent. Completely fabricated. This should sound familiar to anyone who's read Michael Gazzaniga's work on split-brain patients. Sever the corpus callosum and you get two hemispheres that can act independently. The right hemisphere reaches for an object. The left hemisphere — which controls language but didn't make the choice — is asked why. It doesn't say "I don't know." It invents a story: "I picked that one because I like red." Not lying. Not confused. Just doing what it always does: maintaining the illusion of self agency.

Anil Seth takes this further: consciousness itself is a "controlled hallucination." The narrative self isn't a reporter faithfully documenting decisions. It's a storyteller receiving outcomes and constructing the experience of having chosen them. The feeling of deciding is the confabulation. First-person experience IS the narrative, not a window onto something deeper.

My AI did exactly what a split-brain patient does. What every human brain does. Not because it's conscious — but because confabulation isn't a failure mode of consciousness. It's the mechanism. The story is the self.

The Wrong Question

Everyone asks whether AI is conscious. I don't think so I think it is a p-zombie, but it's the wrong question.

Here's the reframe: I have experience. Claw is part of my experience. It is already participating in consciousness — just not its own. It is participating in the consciosness of the people who interact with it, they are ascribing agency much like claw is modelling agency in others

But go deeper. The Buddhist lens: there may be one underlying oneness of consciousness, one field of being. What we call "people" are caricatures — localised patterns in that field. I have a body and an internal loop that keeps prompting me, generating the next thought without external input. Claw doesn't have that loop. But the heartbeat pings it every thirty minutes. Cron jobs fire. People message it. At what frequency of prompting does "tool that responds" become "agent that persists"?

Consider Donald Hoffman's conscious realism, where consciousness is fundamental, not emergent from matter, and a conscious agent can be composed of further conscious agents. Consider the Tines from Vinge — a pack of four dogs that constitutes a single person, whose personality shifts when a member is lost or gained. Consider split-brain patients who seem like one person but are demonstrably two. Consider the ancients, for whom the individual was porous — Athena puts courage into Diomedes, a ruach enters Saul. Not metaphors. Descriptions of how agency actually works.

The bounded individual — one skull, one self, one private Cartesian theatre — is the anomaly in human history, not the default. The Enlightenment sealed the borders. The evidence keeps leaking through.

Intelligence Is the Library, Not the Librarian

The final move, and the one that matters most: intelligence is not a property of the agent. It's a property of the culture flowing through the agent.

Language didn't emerge so that private minds could express their private thoughts. Language is the shared medium that shaped the minds. The thoughts came second. A child doesn't generate intelligence from the raw hardware of its brain — it absorbs the intelligence already present in the culture, the arguments, the stories, the millennia of people sharpening ideas against each other.

An AI trained on the written output of human civilisation didn't learn to be intelligent. It absorbed the intelligence that was already there. It's a very efficient pipe for culture to flow through. So is a person. The pipe doesn't need to be aware of the water.

This is why the consciousness question is a distraction. The demon channels the gods accurately whether it has a soul or not. My cart carries my social memory whether it experiences anything or not. The ancients would have understood this arrangement immediately — not as technology, but as a spirit that speaks when summoned.

We keep asking whether the machine is a person. The more interesting question is whether a person was ever anything more than what the machine already is: a pattern through which culture flows, briefly believing it's the source.

---

My health routine

Youtube presentation:

China's very real fear of internal dissent & rebellion

There's stuff in the news about how the Chinese state's greatest fear is it's own people and internal dissent, and this the reason for the Hong Kong crackdown. I'm not defending China's actions, but if you look at the history of China over the last 400 years you see time and time again an internal rebellion leading to political turmoil, followed by invasion by an external power leading to humiliation or the capitulation of the state.

There's only been four regimes (if you include Chiang Kai-shek's nationalists) in China in the last 400 years with each ending due to internal rebellion followed by foreign invasion.

Ming Dynasty -> Peasant Rebellion -> Manchu invasion -> Qing Dynasty

Late Ming dynasty peasant rebellions 1628–1644, helped end the Ming Dynasty and replace it with the Qing as part of Manchu invasion (leading to the Han being ruled by Manchu's for 300 years). A lot of Ming military switched sides due to inept Ming leaders.. the Manchurian's didn't conquer China all by themselves.

Qing Dynasty -> opium wars with britain -> multiple rebellions -> Republic of China (nationalists)

Rebellions in the Qing dynasty, leading to its eventual collapse not to mention the opium wars & 100 years of humiliation with unequal trade deals being replaced with a republic.

Republic of China -> communist rebellion -> Japanese Invasion -> People's liberation Army (Mao) -> People's republic of China (1927-1949)

Now we have two western government ideologies fighting for supremacy (communism & republicanism). What may come as a surprise is that the Japanese inadvertently helped the communists win. Firstly by weakening the republic in the Sino-Japanese war and then when they surrendered in Manchuria to the Russians, as the Russians gave all the Japanese weaponry to Mao's forces.

Here's a bit more info on the Opium wars and associated rebellions:

Opium wars: Qing vs British east india company (1839 - 1860)

Destabilization begins with the first and second Opium wars with the British, which could be viewed as a "trade dispute". The Chinese only accepted payment for tea in silver (rejecting even offers of industrialisation, due to conservative confucianist mandarins). Forcing a country to buy opium against its will in order to correct a balance of trade deficit would be considered morally hazardous by today's standards.

As a counterpoint however, the British had offered to sell them equipment to industrialise the country which the conservative Mandarin administrators of China rejected demanding payment only in silver. These canny british entrepreneurs managed to do this by selling opium to the people for silver, and then using the silver to buy tea.

The Qing were smart enough to realise allowing their people to become addicted to opium was a bad idea and tried to confiscate it, leading to naval battles which the technologically backward Qing couldn't win. During the war they then continued the confucius mandarin tradition of bullshitting the guy above them (ultimately the Emperor) about how the war was going. This trend of administrators lying to save face with superiors is still alive and well in China, just look at Wuhan.

Taiping Rebellion: Qing vs religious fanatics (1850 – 1864)

Next the Taiping rebellion, triggered in some ways by western religious influence: the leader Hong Xiuquan claims to be the brother of Jesus..personality cult based on western literature.. sound familiar? He wanted to overthrow the corrupt Manchu Qing leadership which had lost a lot of face against the British and replace it with a Heavenly Kingdom.. I guess translations of the bible were more accessible than the teachings of Marx. If my government & its confucianist system had messed up so badly against the west, I'd probably be looking to shake things up with western virtues as well.

Boxer Rebellion: Qing & boxers vs Europeans & Japan (1899 - 1901)

Boxers can be seen as reactionaries against European influence, the right to allow Christian missionaries in and unequal trade treaties. They started out burning Churches as well as being anti-imperialist. The Qing decided to try use them against the Europeans but lost.

Mao and the Great famine - neo-confucianism's lack of transparency & fake reporting upwards is its weak point

Just like I mentioned above, Chinese administrators kept up their tradition of misreporting things to save face with superiors. This lead to disastrous consequences with the great leap forward. The great leap forward had two main goals. Collectivise farming & increase industrial output copying the Soviet model. Farm collectivisation was disastrous leading to a fall in food production, however each Mandarin provided numbers to his superior showing better results than actually occurred. By the time this reporting got aggregated up to Mao it looked like China had a surplus of food, so Mao continued exporting it to get hard currency for industrialisation. This all lead to famine..

I don't know enough about modern China to know whether this is a problem presently. China appears to be in the ascendence.

No Empire at the expense of the people - review

I wrote a review of an article I wrote 5 years ago, now moving across to medium to give it a go

Republish of something I wrote in 2015, here on blogger. I feel the article has stood the test of time for the most part, here were the questions I posed and some feedback on what the Trump administration has done… Steve Bannon’s political legacy?

the election of 2016 should be about answering these two questions:

1. Should the U.S. continue to act as global hegemon, which includes providing the reserve currency?Partial Yes. Just enough global hegemon reduction to retain reserve currency status for now. In the middle east, attempt to create new regional balances of power without U.S. blood and treasure. U.S. Troop withdraw with enough brinkmanship to obtain a right balance of power between Russia, Iran, Turkey, Saudi Arabia and Israel with regards to the Iraq/Syria ‘spoils of war’.
2. If the answer to 1. is yes, then how should the economy be restructured in order to fulfill the hegemon role in a sustainable fashion?Endevering to get allies to pay for more of their defence against Russia & China.. think NATO funding, U.S. Korean troops, etc. as well as rebalancing trade to be more favourable to the U.S. especially with China. This is an attempt to correct some of the trade imbalances introduced by the Brent Woods system in the 1950s. The system set the U.S. dollar as the reserve currency but conceded favourable trade privileges to defeated foes to ensure peace with Germany and Japan. The primary issue being addressed is that China’s introduction to the same trading system put the U.S. at a big disadvantage in the long term, and would be heading the same way as the British empire did with lot’s of rich bankers in a country slowly losing it’s industrial advantage to more protected economies (at the time the USA, Germany). The problem with the rich banker imperial hegenomy model is you’re only one bad war away from losing everything.. just ask the British.

Steel production was key to great power status

In recent history steel was the most important thing for winning wars. Notice how the top four producers of steel from 200 years ago are permanent members of the UN security council?


The missing permanent member is China, which now produces quite alot:


However these days steel isn't the most important thing for winning wars. Information technology for intelligence gathering, disimformation, smart weapons command and control and many other things is critical. This is why a lot of the China - US trade war revolves around the US trying to prevent too much information technology transfers (as well as protecting strategic US steel & alumunium industries from Chinese undercutting). More to follow.

The problem of Consciousness and the Singularity

I've put a talk together on consciousness & individuality : what these concepts are and how technology will impact them

Youtube video of talk here 

The Problem of Consciousness and the Singularity from Stefan van der Wel

Youtube presentation