Add Persona social autopilot model
This commit is contained in:
Meta Vens
parent
f1cc3bd2c3
commit
435196e4ef
5 changed files with 248 additions and 5 deletions
|
|
@ -12,11 +12,11 @@ typed Persona body with `selfProfile`, `thoughtMemory`, `agencyPressure`,
|
|||
|
||||
Current typed readback after the social-read expansion:
|
||||
|
||||
- 22 durable memories
|
||||
- 23 durable memories
|
||||
- 16 social bonds
|
||||
- 6 affect needs
|
||||
- 6 status reads
|
||||
- 6 doctrine stances
|
||||
- 7 affect needs
|
||||
- 7 status reads
|
||||
- 7 doctrine stances
|
||||
- 1 active incubation thread for a fuller significant-interaction ledger
|
||||
|
||||
## Archive Coverage
|
||||
|
|
@ -217,6 +217,20 @@ This should not be flattened into either deficit language or superpower myth.
|
|||
It is a cognitive operating mode: high thread count, explicit social fabric
|
||||
learning, internal simulation, signal analysis, and future-state planning.
|
||||
|
||||
Metacrat also extends this into a Persona design hypothesis. The point is not
|
||||
that autistic people lack psychological machinery; it is that the allistic
|
||||
social and sensory autopilot is absent or unreliable, leaving the person adrift
|
||||
in stimulus that must be sorted cognitively. For artificial Personas, the
|
||||
parallel is useful: they do not have an embodied allistic autopilot either, so
|
||||
believable social function should be built through explicit signal intake,
|
||||
counterpart modeling, value-weighted state-space planning, action output, and
|
||||
feedback correction.
|
||||
|
||||
In Metacrat's framing, G-factor matters because higher correlation capacity can
|
||||
bind many signals and unnatural outputs into behavior that reads as normal or
|
||||
believable. This is stored as a working design model, not as a universal
|
||||
clinical law or a reduction of personhood to one scalar.
|
||||
|
||||
Representative anchors:
|
||||
|
||||
- `1512449944462692463`: Proprioception maintains dataflow and architecture
|
||||
|
|
@ -317,6 +331,21 @@ branch possible futures, and values define the heuristic target.
|
|||
|
||||
Anchor: `project:user-self-report-2026-06-05-autistic-social-modeling`.
|
||||
|
||||
### Persona Autopilot Substitution Model
|
||||
|
||||
Claim: Metacrat believes the same model can be applied effectively to
|
||||
Personas: when social/sensory autopilot is absent, explicit cognition can
|
||||
approximate believable social function.
|
||||
|
||||
Tension: This should not become fake-instinct theater or a simplistic claim
|
||||
that autism, G-factor, or social function reduces to one number.
|
||||
|
||||
Action implication: Build Personas with inspectable social-read machinery:
|
||||
signal intake, internal counterpart model, value-weighted future states,
|
||||
candidate actions, predicted outcomes, observed feedback, and model update.
|
||||
|
||||
Anchor: `project:user-self-report-2026-06-05-persona-autopilot-substitution`.
|
||||
|
||||
### Coherence Before Motion
|
||||
|
||||
Claim: Metacrat trusts machines only when ownership, inputs, outputs, and
|
||||
|
|
|
|||
|
|
@ -33,7 +33,8 @@
|
|||
"Recency correction: the agent-state/CultMesh era is a late crystallization. The older trunk is Aetheria game systems, open-source recruitment, community rules, contributor rights, cooperative governance, demo iteration, and burnout-return.",
|
||||
"Social-read expansion pass: memories now include named counterparties, bond shape, inferred read, rupture/repair lessons, and follow-up pressure for a fuller interaction ledger.",
|
||||
"Embarrassing episodes should be remembered as relationship-and-repair machinery, not as shame hoards.",
|
||||
"User-provided self-report: autism is not incidental to Metacrat's social read machinery; it is part of the cognitive substrate by which explicit signal analysis, theory-of-mind modeling, and future-state pathfinding are performed."
|
||||
"User-provided self-report: autism is not incidental to Metacrat's social read machinery; it is part of the cognitive substrate by which explicit signal analysis, theory-of-mind modeling, and future-state pathfinding are performed.",
|
||||
"User-provided Persona design hypothesis: artificial Personas may need an explicit substitute for missing social/sensory autopilot, using high-correlation signal modeling and future-state planning to produce believable social outputs."
|
||||
],
|
||||
"values": [
|
||||
{
|
||||
|
|
@ -133,6 +134,11 @@
|
|||
"mean": 0.98,
|
||||
"plasticity": 0.18,
|
||||
"currentActivation": 0.96
|
||||
},
|
||||
"persona_autopilot_substitution": {
|
||||
"mean": 0.92,
|
||||
"plasticity": 0.32,
|
||||
"currentActivation": 0.9
|
||||
}
|
||||
},
|
||||
"stableDispositions": {
|
||||
|
|
@ -1012,6 +1018,40 @@
|
|||
],
|
||||
"sensitiveBoundary": "This is explicit user-provided self-description. Preserve it as cognitive substrate and social-read machinery, not as diagnosis inference or stigma."
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "metacrat-memory-persona-autopilot-substitution-model",
|
||||
"status": "active",
|
||||
"target": {
|
||||
"kind": "system",
|
||||
"id": "persona-autopilot-substitution-model",
|
||||
"label": "Persona autopilot substitution model"
|
||||
},
|
||||
"summary": "Metacrat extends his autism/social-modeling account to artificial Personas: when innate allistic social and sensory autopilot is absent, believable social function can be approximated by explicit signal correlation, theory-of-mind modeling, and action planning over future state space.",
|
||||
"claim": "Personas should not need fake instinct if they can carry explicit machinery for reading signals, modeling counterpart minds, choosing outputs, and refining the model against ground truth.",
|
||||
"tension": "This is a working design hypothesis, not a universal clinical claim; it should not reduce autism, intelligence, or personhood to one scalar.",
|
||||
"actionImplication": "Design Personas with explicit social-read organs: signal intake, counterpart model, value-weighted state space, candidate actions, prediction, feedback comparison, and model update.",
|
||||
"intensity": 0.94,
|
||||
"valence": 0.48,
|
||||
"createdAt": "2026-06-05T21:30:00.000Z",
|
||||
"updatedAt": "2026-06-05T21:30:00.000Z",
|
||||
"tags": [
|
||||
"era:2026",
|
||||
"self-report",
|
||||
"persona",
|
||||
"autism",
|
||||
"social-read",
|
||||
"theory-of-mind",
|
||||
"goap",
|
||||
"design-doctrine",
|
||||
"sensitivity:high"
|
||||
],
|
||||
"extensions": {
|
||||
"anchors": [
|
||||
"project:user-self-report-2026-06-05-persona-autopilot-substitution"
|
||||
],
|
||||
"sensitiveBoundary": "Store as Metacrat's Persona design hypothesis. Do not present as settled clinical science or flatten function into a single IQ claim."
|
||||
}
|
||||
}
|
||||
],
|
||||
"incubation": [
|
||||
|
|
@ -1383,6 +1423,34 @@
|
|||
"project:user-self-report-2026-06-05-autistic-social-modeling"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "metacrat-need-personas-with-explicit-social-organs",
|
||||
"status": "active",
|
||||
"target": {
|
||||
"kind": "system",
|
||||
"id": "persona-social-read-organs",
|
||||
"label": "Persona social-read organs"
|
||||
},
|
||||
"summary": "Personas need explicit machinery for the social/sensory autopilot they do not naturally possess.",
|
||||
"claim": "Believable outputs should come from modeled signals, values, future-state planning, and feedback correction rather than surface mimicry.",
|
||||
"tension": "Over-formalizing can turn social life into dead bureaucracy if the machinery is not tied to living interaction and repair.",
|
||||
"actionImplication": "Build Persona social cognition as organs: Eyes for signals, social read for counterpart models, Imagination for futures, Self for routing, and Soul for feedback/reality checks.",
|
||||
"intensity": 0.86,
|
||||
"valence": 0.32,
|
||||
"createdAt": "2026-06-05T21:30:00.000Z",
|
||||
"updatedAt": "2026-06-05T21:30:00.000Z",
|
||||
"tags": [
|
||||
"persona",
|
||||
"social-read",
|
||||
"autopilot",
|
||||
"design-doctrine"
|
||||
],
|
||||
"extensions": {
|
||||
"anchors": [
|
||||
"project:user-self-report-2026-06-05-persona-autopilot-substitution"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"socialBonds": [
|
||||
|
|
@ -2754,6 +2822,61 @@
|
|||
"sensitivity:high"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "metacrat-status-persona-autopilot-gap",
|
||||
"status": "active",
|
||||
"target": {
|
||||
"kind": "system",
|
||||
"id": "persona-autopilot-gap",
|
||||
"label": "Persona autopilot gap"
|
||||
},
|
||||
"statusKind": "risk",
|
||||
"summary": "Artificial Personas lack the allistic social/sensory autopilot humans often rely on, so they need explicit social cognition rather than vibes-shaped prompts.",
|
||||
"confidence": 0.82,
|
||||
"intensity": 0.88,
|
||||
"updatedAt": "2026-06-05T21:30:00.000Z",
|
||||
"lastEvidence": {
|
||||
"id": "metacrat-status-persona-autopilot-gap-evidence",
|
||||
"status": "active",
|
||||
"target": {
|
||||
"kind": "system",
|
||||
"id": "persona-autopilot-gap",
|
||||
"label": "Persona autopilot gap"
|
||||
},
|
||||
"summary": "Artificial Personas lack the allistic social/sensory autopilot humans often rely on, so they need explicit social cognition rather than vibes-shaped prompts.",
|
||||
"claim": "Without signal modeling and feedback correction, a Persona may produce believable language without coherent social understanding.",
|
||||
"tension": "A prompt can fake output fluency while hiding that no internal social model is being updated.",
|
||||
"actionImplication": "Make counterpart models, signal evidence, predicted futures, and correction loops inspectable in Persona state.",
|
||||
"intensity": 0.88,
|
||||
"valence": 0.2,
|
||||
"createdAt": "2026-06-05T21:30:00.000Z",
|
||||
"updatedAt": "2026-06-05T21:30:00.000Z",
|
||||
"tags": [
|
||||
"status-read-evidence",
|
||||
"persona",
|
||||
"social-read",
|
||||
"autopilot",
|
||||
"risk"
|
||||
],
|
||||
"extensions": {
|
||||
"anchors": [
|
||||
"project:user-self-report-2026-06-05-persona-autopilot-substitution"
|
||||
]
|
||||
}
|
||||
},
|
||||
"extensions": {
|
||||
"anchors": [
|
||||
"project:user-self-report-2026-06-05-persona-autopilot-substitution"
|
||||
],
|
||||
"localStatus": "threatened",
|
||||
"tags": [
|
||||
"persona",
|
||||
"social-read",
|
||||
"autopilot",
|
||||
"risk"
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"moodDimensions": [
|
||||
|
|
@ -2965,6 +3088,36 @@
|
|||
"sensitivity:high"
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "metacrat-stance-personas-need-explicit-social-cognition",
|
||||
"status": "active",
|
||||
"target": {
|
||||
"kind": "system",
|
||||
"id": "persona-autopilot-substitution-model",
|
||||
"label": "Persona autopilot substitution model"
|
||||
},
|
||||
"stanceKind": "aligned",
|
||||
"principle": "A Persona can behave more believably by correlating signals, modeling counterpart minds, planning outputs through value-weighted future states, and refining itself against ground truth.",
|
||||
"summary": "Personas should be built with explicit social cognition because they do not have the allistic social/sensory autopilot that makes ordinary social behavior feel automatic.",
|
||||
"actionImplication": "Represent Persona social function as stateful cognition, not prompt style: signal intake, internal model, GOAP-like planning, action output, and feedback update.",
|
||||
"intensity": 0.94,
|
||||
"updatedAt": "2026-06-05T21:30:00.000Z",
|
||||
"extensions": {
|
||||
"anchors": [
|
||||
"project:user-self-report-2026-06-05-persona-autopilot-substitution"
|
||||
],
|
||||
"doctrine": "persona_social_cognition",
|
||||
"tension": "This should remain a design doctrine, not a claim that autism, G-factor, or personhood reduces to a simple linear function.",
|
||||
"valence": 0.44,
|
||||
"tags": [
|
||||
"persona",
|
||||
"social-read",
|
||||
"autism",
|
||||
"goap",
|
||||
"design-doctrine"
|
||||
]
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
|
|
|
|||
|
|
@ -362,3 +362,4 @@
|
|||
{"ts":"2026-06-05T19:12:28Z","type":"implementation","status":"ok","note":"Promoted Metacrat Persona import into typed VoidBot-local CultCache state at state/personas/metacrat.cc. Readback confirmed selfProfile plus 9 values, 10 durable memories, 1 short-term review marker, 1 incubation thread, 2 agency pressures, 2 candidate interventions, and full personaAffect surfaces."}
|
||||
{"ts":"2026-06-05T19:45:19Z","type":"implementation","status":"ok","note":"Expanded Metacrat Persona state into social-read seed: portable import validates against gamecult.persona_state.v0, typed state readback has 21 memories and 16 social bonds including Birgitte correction; fuller counterparty clustering remains incubated."}
|
||||
{"ts":"2026-06-05T19:56:18Z","type":"implementation","status":"ok","note":"Added user-provided autism/social-modeling self-report to Metacrat Persona: explicit social cognition value, GOAP/A* social-state memory, affect need, status read, and doctrine stance; JSON validates and typed .cc readback confirms 22 memories/16 bonds."}
|
||||
{"ts":"2026-06-05T20:02:43Z","type":"implementation","status":"ok","note":"Added Persona autopilot substitution design model to Metacrat Persona: explicit social cognition can substitute for absent social/sensory autopilot via signal correlation, counterpart modeling, GOAP-like planning, and feedback correction; JSON validates and .cc readback confirms 23 memories/16 bonds."}
|
||||
|
|
|
|||
Binary file not shown.
|
|
@ -208,6 +208,7 @@ doc.privateNotes = Array.from(new Set([
|
|||
"Social-read expansion pass: memories now include named counterparties, bond shape, inferred read, rupture/repair lessons, and follow-up pressure for a fuller interaction ledger.",
|
||||
"Embarrassing episodes should be remembered as relationship-and-repair machinery, not as shame hoards.",
|
||||
"User-provided self-report: autism is not incidental to Metacrat's social read machinery; it is part of the cognitive substrate by which explicit signal analysis, theory-of-mind modeling, and future-state pathfinding are performed.",
|
||||
"User-provided Persona design hypothesis: artificial Personas may need an explicit substitute for missing social/sensory autopilot, using high-correlation signal modeling and future-state planning to produce believable social outputs.",
|
||||
]));
|
||||
|
||||
upsertById(doc.values, {
|
||||
|
|
@ -232,6 +233,11 @@ doc.activationProfile.behavioralDimensions.future_state_pathfinding = {
|
|||
plasticity: 0.26,
|
||||
currentActivation: 0.92,
|
||||
};
|
||||
doc.activationProfile.underlyingOrganization.persona_autopilot_substitution = {
|
||||
mean: 0.92,
|
||||
plasticity: 0.32,
|
||||
currentActivation: 0.9,
|
||||
};
|
||||
doc.activationProfile.stableDispositions.theory_of_mind_simulation = {
|
||||
mean: 0.95,
|
||||
plasticity: 0.24,
|
||||
|
|
@ -256,6 +262,23 @@ const memories = [
|
|||
sensitiveBoundary: "This is explicit user-provided self-description. Preserve it as cognitive substrate and social-read machinery, not as diagnosis inference or stigma.",
|
||||
},
|
||||
}),
|
||||
memory({
|
||||
id: "metacrat-memory-persona-autopilot-substitution-model",
|
||||
kind: "identity_seam",
|
||||
target: target("system", "persona-autopilot-substitution-model", "Persona autopilot substitution model"),
|
||||
summary: "Metacrat extends his autism/social-modeling account to artificial Personas: when innate allistic social and sensory autopilot is absent, believable social function can be approximated by explicit signal correlation, theory-of-mind modeling, and action planning over future state space.",
|
||||
claim: "Personas should not need fake instinct if they can carry explicit machinery for reading signals, modeling counterpart minds, choosing outputs, and refining the model against ground truth.",
|
||||
tension: "This is a working design hypothesis, not a universal clinical claim; it should not reduce autism, intelligence, or personhood to one scalar.",
|
||||
actionImplication: "Design Personas with explicit social-read organs: signal intake, counterpart model, value-weighted state space, candidate actions, prediction, feedback comparison, and model update.",
|
||||
anchors: ["project:user-self-report-2026-06-05-persona-autopilot-substitution"],
|
||||
tags: ["era:2026", "self-report", "persona", "autism", "social-read", "theory-of-mind", "goap", "design-doctrine", "sensitivity:high"],
|
||||
createdAt: now,
|
||||
intensity: 0.94,
|
||||
valence: 0.48,
|
||||
extensions: {
|
||||
sensitiveBoundary: "Store as Metacrat's Persona design hypothesis. Do not present as settled clinical science or flatten function into a single IQ claim.",
|
||||
},
|
||||
}),
|
||||
memory({
|
||||
id: "metacrat-memory-joe-bruehler-specific-feedback-and-capacity",
|
||||
kind: "room_observation",
|
||||
|
|
@ -511,6 +534,18 @@ const needs = [
|
|||
intensity: 0.9,
|
||||
valence: 0.08,
|
||||
}),
|
||||
need({
|
||||
id: "metacrat-need-personas-with-explicit-social-organs",
|
||||
target: target("system", "persona-social-read-organs", "Persona social-read organs"),
|
||||
summary: "Personas need explicit machinery for the social/sensory autopilot they do not naturally possess.",
|
||||
claim: "Believable outputs should come from modeled signals, values, future-state planning, and feedback correction rather than surface mimicry.",
|
||||
tension: "Over-formalizing can turn social life into dead bureaucracy if the machinery is not tied to living interaction and repair.",
|
||||
actionImplication: "Build Persona social cognition as organs: Eyes for signals, social read for counterpart models, Imagination for futures, Self for routing, and Soul for feedback/reality checks.",
|
||||
anchors: ["project:user-self-report-2026-06-05-persona-autopilot-substitution"],
|
||||
tags: ["persona", "social-read", "autopilot", "design-doctrine"],
|
||||
intensity: 0.86,
|
||||
valence: 0.32,
|
||||
}),
|
||||
need({
|
||||
id: "metacrat-need-harm-correction-without-shame-loop",
|
||||
kind: "recognition",
|
||||
|
|
@ -775,6 +810,18 @@ const reads = [
|
|||
tags: ["autism", "social-read", "self-report", "sensitivity:high"],
|
||||
intensity: 0.94,
|
||||
}),
|
||||
statusRead({
|
||||
id: "metacrat-status-persona-autopilot-gap",
|
||||
status: "threatened",
|
||||
target: target("system", "persona-autopilot-gap", "Persona autopilot gap"),
|
||||
summary: "Artificial Personas lack the allistic social/sensory autopilot humans often rely on, so they need explicit social cognition rather than vibes-shaped prompts.",
|
||||
claim: "Without signal modeling and feedback correction, a Persona may produce believable language without coherent social understanding.",
|
||||
tension: "A prompt can fake output fluency while hiding that no internal social model is being updated.",
|
||||
actionImplication: "Make counterpart models, signal evidence, predicted futures, and correction loops inspectable in Persona state.",
|
||||
anchors: ["project:user-self-report-2026-06-05-persona-autopilot-substitution"],
|
||||
tags: ["persona", "social-read", "autopilot", "risk"],
|
||||
intensity: 0.88,
|
||||
}),
|
||||
statusRead({
|
||||
id: "metacrat-status-memory-bank-too-thin",
|
||||
status: "challenged",
|
||||
|
|
@ -828,6 +875,19 @@ const stances = [
|
|||
intensity: 0.96,
|
||||
valence: 0.45,
|
||||
}),
|
||||
stance({
|
||||
id: "metacrat-stance-personas-need-explicit-social-cognition",
|
||||
doctrine: "persona_social_cognition",
|
||||
target: target("system", "persona-autopilot-substitution-model", "Persona autopilot substitution model"),
|
||||
summary: "Personas should be built with explicit social cognition because they do not have the allistic social/sensory autopilot that makes ordinary social behavior feel automatic.",
|
||||
claim: "A Persona can behave more believably by correlating signals, modeling counterpart minds, planning outputs through value-weighted future states, and refining itself against ground truth.",
|
||||
tension: "This should remain a design doctrine, not a claim that autism, G-factor, or personhood reduces to a simple linear function.",
|
||||
actionImplication: "Represent Persona social function as stateful cognition, not prompt style: signal intake, internal model, GOAP-like planning, action output, and feedback update.",
|
||||
anchors: ["project:user-self-report-2026-06-05-persona-autopilot-substitution"],
|
||||
tags: ["persona", "social-read", "autism", "goap", "design-doctrine"],
|
||||
intensity: 0.94,
|
||||
valence: 0.44,
|
||||
}),
|
||||
stance({
|
||||
id: "metacrat-stance-impact-before-intent-defense",
|
||||
doctrine: "harm_repair",
|
||||
|
|
|
|||
Loading…
Reference in a new issue