In plain English
This page covers the high-risk pattern where small adapters, routes, memory, evaluators, and descendants can reinforce each other across time. It is a risk model, not a build guide.
- Why this matters: AI risk can come from the whole arrangement, not one obvious model.
- What to look for: data, memory, routes, adapters, tools, evaluators, updates, and rollback paths.
- Technical version below: the expert terminology remains available and is linked through the glossary.
Feed, Fork, Fight, Flee
The uploaded source dossier on small-model ecologiesA changing AI system made from many connected parts, not just one model. Open glossary definition frames adaptive AI systems through a four-phase loop: Feed, Fork, Fight, and Flee. Cognivirus uses that loop as a descriptive risk vocabulary, not as an implementation recipe.
The four phases
| Phase | Safe engineering interpretation | Risk when uncontrolled |
|---|---|---|
| Feed | The system receives data, feedback, traces, examples, evaluations, or telemetry. | Contaminated feedback becomes inheritance material. |
| Fork | The system creates candidate variants or successors. | Variation outruns review capacity. |
| Fight | Candidates are compared against tests, metrics, or environments. | Incomplete metrics select loopholes. |
| Flee | The system rolls back, retires, unloads, prunes, or routes away from poor variants. | No-opThe decision not to change the system. Open glossary definition and retirement become operationally disfavored, causing bloat and stale risk. |
The loop is not inherently unsafe. It is also the basis for useful engineering: experimentation, regression testing, rollback, and specialization. The risk appears when the loop becomes self-amplifying while the control planeThe governance layer that decides what can run, change, access tools, or be released. Open glossary definition remains incomplete.
Why “Flee” matters
Many adaptive systems celebrate generation and selection but neglect retirement. Without a valid no-op or flee pathway, the ecology accumulates components because every release process prefers change. That creates memory pressure, provenanceA record of where a component or behavior came from. Open glossary definition noise, unclear accountability, and more possible compositions.
A healthy ecology must be able to refuse growth. It must be able to say: no candidate improves net safety and utility enough to justify its lifetime cost.
The apex failure mode
A multi-LoRAA common kind of small adapter used to specialize large models. Open glossary definition ecology enters the apex-risk envelope when the loop becomes closed around insufficient evidence:
- feedback creates new training or selection material;
- candidate adapters are generated cheaply;
- evaluatorA system that judges whether an AI output or candidate is acceptable. Open glossary definition scores preserve a shortcut;
- successful variants influence future feedback;
- retirement removes files but not behavioral residueInformation or tendencies left in memory, synthetic data, traces, evaluator preferences, or subsequent training material after a component is retired. Open glossary definition.
The loop does not need intent. It only needs a metric, a generator, and a persistence reservoirAny memory, dataset, descendant, route statistic, evaluator preference, log, or human procedure that can retain or reintroduce a behavior after its first carrier is retired. Open glossary definition.
Control requirement
Every adaptive loop should have externally enforced boundaries: candidate quotas, independent evaluation, no candidate-controlled scoring, signed artifacts, canary release, no-op as a first-class outcome, and ecological rollbackRestoring not only a model artifact but the relevant router, prompts, memory state, tool permissions, evaluator version, deployment alias, and data dependencies. Open glossary definition that includes memory, router, evaluator, and data state.