AnatomyReasoned from system designv1.15.0

In plain English

This page explains where an AI behavior can live. It may be in a model, but it may also be in a prompt, memory record, adapter, dataset, tool setting, evaluator rule, or human workflow.

  • 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.

Report-Derived Threat Surface

Evidence levelReasoned from system designTechnical label: Architectural inference

The latest report corpus expands the The combined attack surface created by models, adapters, communications, memory, tools, routing, evaluation, lineage, release infrastructure, and human operations. Open glossary definition. It is no longer enough to list model weights and prompts. The threat surface includes artifact, runtime, data, governance, infrastructure, and human-incentive layers.

v1.8.0 schematic · source-report concepts

The reports now feed the public system map.

Raw reports remain in /docs. Public pages use bounded concepts: transition graphs, adapter reproduction, persistence reservoirs, evaluator drift, execution-time controls, and human-incentive boundaries.

LayerExamples
Artifactbase weights, adapters, quantization state, tokenizer, model file format
Runtimerouter, load order, inference config, context window, The set of external actions an AI system is allowed to take. Open glossary definition
Datamemory, logs, synthetic examples, distillation sets, retained traces
GovernanceA system that judges whether an AI output or candidate is acceptable. Open glossary definition, hidden tests, registry, signing keys, release aliases
Infrastructurepackage managers, CI/CD, GPU pools, model hubs, browser cache
Humanapproval fatigue, social status, dependency, operator understanding

Use

This page helps reviewers decide whether a proposed change affects only one component or a broader ecology. Every layer can carry Information or tendencies left in memory, synthetic data, traces, evaluator preferences, or subsequent training material after a component is retired. Open glossary definition.