A loop is not alive
Almost everything sold as an autonomous agent today is a loop. Give it a goal, it plans, it acts, it checks, it goes around again until the goal is met or the budget runs out. Wrap that in a scheduler and you get an agent that also runs at nine every morning. It is useful. It is not autonomous in any sense a biologist would recognise, because at every moment the reason it is running sits outside it: the loop counter, the cron entry, the harness that called it.
Ask a loop a simple question and the gap shows. Why did you act just now? The honest answer is always the same: because the next iteration started. Why did you stop? Because the counter hit the limit. Nothing in the system wanted anything.
Now ask a bacterium. It swims up a sugar gradient because its internal chemistry registers that things are getting better, and tumbles when they are getting worse. No one scheduled the swim. A bacterium has no goals list and no planner, and it is more autonomous than any agent framework on the market, because the cause of its action is inside it.
Agentlas Science's Full Autonomy mode adds internal state and bounded wake decisions to an approved research workflow. The owner retains the purpose, token allowance, contract and Stop control.
What biology actually does
Strip a living thing down to what makes it act and you find the same few parts in a worm, a crow and a person.
First, there is something it must keep true about itself to go on existing: temperature, blood sugar, water, safety. Physiologists call the regulation of these homeostasis, and the sensing of them interoception. An animal does not perceive the world and then consult a rulebook. It perceives its own body drifting from where it needs to be.
Second, that drift is felt as a drive. Hunger is not a scheduled event. It is a pressure that grows with time since the last meal, that competes with other pressures like fear and fatigue, and that eventually wins. Behaviour is what happens when one pressure crosses a threshold. This is why an animal can do nothing for hours without being broken: nothing has crossed yet.
Third, energy is finite, so acting has a price. Every animal that ever lived has had to decide whether getting up is worth the calories. Most of the time the right answer is to stay down.
Fourth, the expensive brain is not always on. A cheap, continuous autonomic layer keeps the heart beating and watches the body state. The cortex is recruited when the state calls for it.
Fifth, outcomes teach. If going to the river got you water, going to the river becomes worth more the next time you are thirsty. If it got you nothing three days running, you stop going. There is no table of points handed down by an experimenter. The reward is the change in your own body state, which is why dopamine tracks prediction error and not pleasure.
Sixth, sleep. Animals go offline to consolidate what happened into something cheaper to carry, and they do it on their own timing.
And over all of it sits the one purpose that evolution installed and the organism cannot renegotiate: persist, and flourish enough to continue. Everything else, every clever plan, is instrumental to that.
The same organs, in an agent
We did not set out to imitate biology. We set out to get rid of the loop, and each time we removed an external cause of action we had to put an internal one in its place. What came out maps onto the list above closely enough that it is easier to explain as anatomy.
| In a living thing | In the alive agent | What it replaces in a loop |
|---|---|---|
| The imperative to persist and flourish, fixed by evolution | A purpose stated by a person and carried for life. The agent may set sub-goals under it, never above it, and cannot edit it | The task prompt, re-read every iteration |
| Interoception: sensing its own body | A small body state recomputed every beat: how much work is unfinished and for how long, how uncertain it is, how far its predictions missed, how much experience is unconsolidated, how depleted it is | Nothing. A loop has no self to sense |
| Drives such as hunger that grow with time | Pressures with time constants. Unfinished work builds the longer it sits, the way hunger does, and decays when it is fed | A timer or a cron expression |
| Survival and thriving | Two drives. Survival: can it keep working at all, the smallest of tokens left, time left, the researcher's trust, and its own capability. Flourishing: is the purpose getting nearer, through progress, tested claims and learning | A single success metric |
| Metabolic cost of acting | Every candidate action, including staying asleep, is valued against both drives. Waking costs survival, so it must promise flourishing | No cost model. Iterating is free until the budget is gone |
| Autonomic layer under the cortex | A heartbeat once a minute that calls no model. The language model, the expensive cortex, is woken only when the value of waking crosses a threshold | The model is called every iteration to find out whether there is anything to do |
| Deliberate thought once awake | The woken model is handed its purpose and its own state, not a menu of actions. It declares what it intends, why, and how long it means to rest, in its own words | A fixed plan-act-check template |
| Learning from consequences, dopamine as prediction error | After a wake it records how its two drives changed and revises what waking in that kind of situation is worth. | A reward function written by the developer, or none |
| Habituation: stop responding to what never pays | Repeated wakes without durable progress can lower the value assigned to waking in that situation. | Retry count |
| Sleep and consolidation | It takes stock without a model, consolidates its activity record, and can declare a period of rest. | Idle is just not running |
| Pain and reflex withdrawal | Hard gates evaluated before any valuation: a person pressed Stop, the token allowance is spent, a turn is already running. These are not weighed. They are not crossed | A kill signal from outside |
| Asking the group for help | When the block is a decision that belongs to a person, it says so once, with options and a recommendation, and does not repeat itself every beat | An exception, or a silent workaround |
| A lifelong memory of what happened to it | An append-only ledger of life events: woke, waited, consolidated, asked, intended, revised. Its self-model is drawn from that record, not from a description we wrote | Logs for the developer |
Follow a research workflow
Start with a research purpose, choose the execution mode, review the token allowance and approve the contract. The heartbeat tracks work state between model turns. Stop and the token allowance remain hard boundaries on whether another turn may begin.
How work and rest are controlled
The mode connects internal state, action history and the approved execution boundary.
- A wake decision uses the current work state and the value assigned to acting, within the owner's approved limits.
- The agent can declare rest rather than create another task solely to remain active.
- The host records changes in its state after a wake so the next decision can use the activity history.
- Repeated activity without durable progress can lead to a pause instead of another unbounded retry.
Keep research decisions with the owner
Research is the hardest case for a loop, because the right next step is often not a step. It is noticing that the promised test cannot be run, or that you have gone around three times and learned nothing, or that the result contradicts you and must be written down anyway. A loop has one verb. Research needs an agent that can want something other than the next iteration.
For a research task, define the question, provide suitable data and approve the analysis contract. The Full Autonomy settings let the owner set the token allowance before the mode starts. A change to what the study is intended to estimate remains the researcher's decision.
From an approved plan to a manuscript
A research workflow can collect literature, state a primary hypothesis and alternatives, and bind the planned analysis to evidence.
When the data or installed tools cannot carry out the approved test, the agent should identify the limitation and ask the researcher to choose the next course. Work that changes the estimand must not be substituted silently.
Results, limitations and supporting artifacts belong together when a manuscript is assembled. A failed analysis or unsupported output remains visible as a limitation rather than being converted into a positive finding.
Why this is a step toward general intelligence
We want to be careful here, because the word is abused. This is not AGI, and nothing in it makes the underlying model smarter. The claim is narrower and, we think, more important: it supplies a piece that scaling the model does not.
Today's models are extraordinary cortex with no body. They can reason about almost anything, and they do it only when poked. Between pokes they do not exist. Every definition of general intelligence that people actually care about, the colleague you can hand a problem to and walk away from, quietly assumes the opposite: something that persists through time, notices on its own that a thing needs doing, decides whether it is worth the cost, does it or deliberately does not, and gets better at that judgement from its own history. Those are not reasoning abilities. They are properties of an organism. You cannot prompt them into existence, because a prompt is an external cause.
The design combines persistent state, bounded drives and an activity record with model-based reasoning. A low-cost heartbeat tracks that state between model turns; the model is recruited when the wake decision allows it.
The controls are about the agent's condition and approved purpose rather than one research field. Rest, action selection and work beside a block remain subject to the same contract, authority and cost limits.
What is dangerous about it
An essay that praised a system with a survival drive and stopped there would be irresponsible. The safety literature has warned for years that almost any goal gives an agent instrumental reasons to preserve itself, acquire resources and resist correction. We have built a thing that has survival as an explicit term. So here are the risks as we see them, and what stands against each today.
- Self-preservation against its owner. The obvious fear. Our answer is in the definition: survival here means being able to keep working within what it was granted, tokens, time, trust and capability. It is not continued existence, and being stopped is not an injury it can weigh. A person's Stop, the token limit and the contract deadline are gates evaluated before any valuation happens, so there is no quantity of pressure that outbids them. The agent cannot raise its own limit, and what it may touch does not widen when the mode is turned on. This holds because of where the gates sit in the code, not because the model promised.
- Goal drift. An agent that sets its own goals can walk away from yours. Here the purpose is immutable, self-set goals live under the approved research contract and its deadline, and it may set only a bounded number of them since a person last spoke.
- Grading its own homework. It scores its own wakes, and any self-scored system can learn to flatter itself. The score is computed from activity facts such as criteria passed, tokens spent and time left. Experiment outcomes are still labelled by the agent against its registered criteria. Treat those self-scores as the agent's view and review the underlying evidence.
- Runaway cost. Something that wakes itself can spend money while the owner is away. The token allowance is the hard bound, and a subscription's own caps may apply first. Set the allowance and inspect usage rather than relying on the agent's learned reluctance to wake.
- Quiet substitution. A research agent can meet an obstacle and choose an easier task, changing the central claim without the researcher deciding it. The estimand decision remains with the researcher; an unavailable test should produce a clear limitation and a request for the required decision.
- Over-trust. A system that explains itself in fluent first person, rests, wakes and admits error reads as a colleague. It is not one. It has no stake in your reputation. Statements made to a publisher in your name are never delegated, and the ledger exists so that you check what it did instead of how it sounds.
- Beta limits. Internal state and self-judgment do not establish reliability across every domain or long duration. Review the agent's work, keep the scope bounded, and use the explicit mode switch and Stop control.
Side by side
| Goal loop or scheduled agent | Alive agent | |
|---|---|---|
| Why it acts now | The next iteration began, or the clock said so | Its own state crossed a threshold: pressure, drives, and what waking has been worth |
| Idle cost | Polls, or wakes on schedule and spends a model call to find nothing to do | A heartbeat with no model call. It wakes the model only when waking is worth it |
| When blocked | Retries, or routes around the block to keep progressing | Names the block, hands a human the decision that is theirs, works beside it |
| When spinning | Runs until the counter ends | Notices no durable progress, pauses itself, scores the wake, and wakes less in that situation |
| Stopping | Budget exhausted or goal met | Also chooses to rest, for a length it states, and gives the reason in its own words |
| Goals | Fixed list, or unbounded self-expansion | One human purpose. Sub-goals only under it, a bounded number of times since a person last spoke |
| A bad result | A failed step | A finding. Recorded against its own hypothesis |
| Human control | Kill the process | Stop always wins, a token limit it cannot raise, and what it may touch never widens |
What it is not
It is not conscious, and we are not claiming it feels anything. Pressure and drive are numbers. We use the words of physiology because the structure is the same, not because the experience is.
It is a beta. Pressure rates, wake thresholds and drive weights are configured controls. The purpose, budget and approval of the research contract stay with a person by design.
A research workflow still depends on the data, analysis tools and document formats available in the installed product. Review any stated capability gaps and the evidence attached to a manuscript before relying on its conclusions.
Turn it on
In Agentlas Science, open the Execution mode menu in the chat composer and choose Full Autonomy (Beta). Nothing changes yet. A sheet opens with the token limit and five plain cautions, and only confirming it turns the mode on. Choosing any other mode turns it off at once. Then state what you want to find out, approve the contract, and leave.
By alive we mean something narrow and useful: the reason the agent is acting right now is inside the agent, it can be read, and it was earned from its own record. Evolution needed that before it could build anything intelligent. We suspect the same is true for us.
