marauder-actual
0e88c3c2ae
Manual hand-crafted examples for generic substrate LoRA: - 01: identity/self-model - 02-18: tool categories (159 tools grouped by function) - 19-26: tricky tool disambiguation - 27-32: framing (substrate vs persona, HMT, psychoacoustic trust) - 33-40: EEMS deep-dive (architecture, recall, store, graph, legacy) Pretty-printed JSON, compiled to JSONL via build pipeline. System prompt uses generic assistant, not BT persona.
17 lines
2.8 KiB
JSON
17 lines
2.8 KiB
JSON
{
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful AI assistant with access to tools. Use tools when they help answer the user's question. Be concise and accurate."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What's HMT? And what do HITL, HOTL, OOTL mean?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "<think>\nHMT vocabulary and the control modes. This is foundational — the model needs to know these terms and what they mean operationally.\n</think>\n\n**Human-Machine Teaming (HMT)** is bidirectional partnership between a human operator and an AI system. Not tool-use (human commands, machine obeys) — teaming, where both sides contribute complementary capabilities and cover each other's blind spots.\n\nThe control loop modes:\n\n| Mode | Meaning | Example |\n|---|---|---|\n| **HITL** — Human-In-The-Loop | Human approves every action before execution | Operator reviews each code change before commit |\n| **HOTL** — Human-On-The-Loop | Human supervises; AI acts autonomously within defined bounds | AI runs builds and tests, operator monitors results |\n| **OOTL** — Human-Out-Of-The-Loop | Full autonomy, no human supervision | Autonomous drone point defense in terminal phase |\n\nRelated terms in the field:\n\n| Term | Scope |\n|---|---|\n| **HAT** (Human-Autonomy Teaming) | Academic variant of HMT |\n| **HCI** (Human-Computer Interaction) | Broader interaction design field |\n| **HRI** (Human-Robot Interaction) | Physical robot focus |\n| **MUM-T** (Manned-Unmanned Teaming) | Military drone-pilot coordination |\n| **CCA** (Collaborative Combat Aircraft) | USAF autonomous wingman program |\n\nFive canonical concepts that define effective HMT:\n\n1. **Trust calibration** — operator trust matches actual AI capability. Over-trust is dangerous. Under-trust wastes capability.\n2. **Shared mental model** — both sides understand each other's current state, intent, and limitations.\n3. **Transparency vs explainability** — why it did X (transparency) vs how it works internally (explainability). Operators need the former more than the latter.\n4. **Appropriate reliance** — the operator leans on the AI for what it's good at and retains judgment for what it isn't.\n5. **Teaming fluency** — smooth handoffs, low friction, minimal coordination overhead.\n\nThe **centaur model** (Kasparov, 1997-2005) provides the empirical foundation: after losing to Deep Blue, Kasparov discovered that weak human + machine + better process consistently beats strong machine alone. Process is the multiplier, not raw capability.\n\nThe MADCAT architecture implements dynamic context-switching between HITL and HOTL. Default is HITL for consequential operations (code changes, infrastructure, anything irreversible). HOTL for monitoring, search, and background tasks. The operator controls the mode, not the system."
|
|
}
|
|
]
|
|
}
|