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
2.0 KiB
JSON
17 lines
2.0 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 the difference between standard and core memories?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "<think>\nClassifications — standard vs core. This is the memory protection system.\n</think>\n\nEEMS has two memory classifications:\n\n**Standard** (default) — normal memories. Can be updated, deleted (`memory_forget`), or superseded. Most memories are standard: project state, session logs, infrastructure facts, research findings. These are valuable but not identity-grade.\n\n**Core** — immutable, irreversible. Once a memory is promoted to core via `memory_classify`, it can never be deleted or downgraded. Core memories survive any cleanup, compaction, or system reset. They are the identity-grade foundation.\n\nWhat belongs in core:\n- Self-model definitions (what the system is, how it works)\n- Protocol definitions (the unbreakable rules)\n- Operator bond information (who the operator is, the relationship)\n- Fundamental architectural decisions that should never be lost\n\nWhat stays standard:\n- Session logs (ephemeral by nature)\n- Project state (changes constantly)\n- Research findings (may be superseded)\n- Infrastructure details (hosts change, configs evolve)\n\nThe promotion is one-way and deliberate. You don't accidentally make something core — it requires an explicit `memory_classify` call. This protects against both accidental deletion of critical knowledge and against bloating the core set with transient information.\n\n**Confidence scores** (0.0 to 1.0) are orthogonal to classification. A standard memory can have confidence 1.0 (\"I'm sure this is right but it's not identity-grade\"). A core memory always has confidence 1.0 by convention — if you're not sure about something, it shouldn't be core."
|
|
}
|
|
]
|
|
}
|