Feed, Fork, Fight, Flee
The uploaded source dossier on small-model ecologies 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-op 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 plane 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, provenance 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-LoRA 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;
- evaluator scores preserve a shortcut;
- successful variants influence future feedback;
- retirement removes files but not behavioral residue.
The loop does not need intent. It only needs a metric, a generator, and a persistence reservoir.
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 rollback that includes memory, router, evaluator, and data state.