diff --git a/docs/research/personality-model-roadmap.md b/docs/research/personality-model-roadmap.md index e35b6df..9abe8d3 100644 --- a/docs/research/personality-model-roadmap.md +++ b/docs/research/personality-model-roadmap.md @@ -77,7 +77,32 @@ That matters. We do not want a personality museum. We want a machine that update The future personality layer should not be one trait sheet. It should be a stack. -### 1. Stable-ish Dispositions +### 1. Underlying Organization + +This sits deeper than ordinary traits. + +Track things like: + +- self-coherence +- contingent worth +- shame sensitivity +- attachment hunger +- threat sensitivity +- reciprocity capacity +- mentalization quality +- authenticity tolerance +- mask rigidity + +This is the layer that answers questions like: + +- how stable does the self feel from the inside +- how much does worth depend on approval, utility, purity, admiration, or submission +- how catastrophic does exposure or diminishment feel +- how much of the self must be performed to remain lovable or safe + +This matters because some personalities are not merely "high in trait X." Some are organized around a damaged or contingent self that must be defended, staged, concealed, or externally regulated to stay upright. + +### 2. Stable-ish Dispositions These are slow-changing tendencies: @@ -92,7 +117,7 @@ These are slow-changing tendencies: These are the closest thing to trait structure. They change, but slowly. -### 2. Behavioral Dimensions +### 3. Behavioral Dimensions These are the live handles we actually use in social and economic simulation: @@ -109,7 +134,7 @@ These are the live handles we actually use in social and economic simulation: These can be updated from remembered incidents, repeated patterns, and institutional pressure. -### 3. Relationship State +### 4. Relationship State This is where the real blood is. @@ -128,7 +153,37 @@ Per target person, group, faction, or institution, track things like: This is where "they are warm in general" becomes "they are warm with her but clipped with him and terrified of them." -### 4. Situational State +### 5. Performed Self And Defensive Style + +Everyone performs to some degree. The interesting question is not whether a mask exists, but how necessary and rigid it is. + +Track presentation strategies such as: + +- charm +- compliance +- superiority +- detachment +- seductiveness +- martyrdom +- competence theater +- moral theater +- cultivated opacity + +For some agents this is just social polish. For others it is part of the load-bearing architecture of the self. + +That means: + +- what is revealed is not identical to what is true +- concealment is not mere absence of data +- performance style is itself data about how the person survives other minds + +This is also where we should model the distinction between: + +- ordinary social performance +- strategic impression management +- defensive false-self maintenance + +### 6. Situational State These are transient modifiers: @@ -144,7 +199,7 @@ These are transient modifiers: These should tilt behavior without being mistaken for identity. -### 5. Goals And Value Hierarchy +### 7. Goals And Value Hierarchy Personality without priorities is decorative plumbing. @@ -158,6 +213,34 @@ Track: That is what turns temperament into decisions. +## A Note On Masks, Personality Disorder, And Performed Selves + +One of the important corrections to simplistic personality modeling is that people do not always reveal who they are, and they may not fully know who they are in any clean or integrated sense either. + +Everyone wears a mask to some extent. That part is normal. But some people are organized much more heavily around performance because the self they built early on was contingent: lovable only when useful, safe only when compliant, coherent only when mirrored correctly. + +That distinction matters. + +The model should allow for the possibility that: + +- a person has an underlying organization that is more fragile than their surface suggests +- the performed self exists to regulate other people as much as to express anything authentic +- injury to the mask can feel like injury to existence itself +- oscillation between charm, contempt, neediness, distance, compliance, and control is not random inconsistency but the phenomenon we are trying to model + +So we should not ask only: + +- what trait does this line reveal + +We should also ask: + +- what is being defended +- what must be maintained +- what threatens the shell +- how much room does this person allow for unperformed self + +That is part of why broad trait systems are too tidy for the thing we want. + ## Specific Improvements Worth Adding These were not properly banked elsewhere and should stop living only in chat residue. @@ -172,12 +255,20 @@ The next promising additions are: - desire for closeness, reassurance, fusion, or privileged access - `Distance-Seeking` - need for space, reluctance to be known, aversion to pressure or intimacy +- `Mask Rigidity` + - how tightly the performed self must be maintained under observation +- `Shame Reactivity` + - how catastrophic diminishment, correction, exposure, or failure feels +- `Impression-Management Intensity` + - how actively the person curates what others are allowed to see These matter because the current model can tell "anxious" from "rigid," but it cannot yet cleanly tell: - clingy from avoidant - intermittently intense from steadily difficult - unstable from merely suspicious +- ordinary social polish from defensive self-performance +- insecurity from shell-maintenance panic ### Split Social Stance From Thinking Style @@ -195,6 +286,26 @@ We should separately track something like `project-thinking style`, including te That matters for Aetheria populations and consumer behavior even when there is no direct social confrontation in view. +### Split Underlying Organization From Surface Presentation + +Right now the model is mostly concerned with what the agent sounds like. + +That is not enough. + +We should explicitly separate: + +- underlying organization +- performed self +- situational state +- expressed signal + +That lets the system model cases where: + +- the surface is charming but the underlying relationship stance is instrumental +- the surface is cold but the underlying issue is shame or fragility +- the surface is compliant while resentment and dependency accumulate underneath +- the speaker is actively obfuscating traits to preserve a shell + ### Add Reflection And Consolidation The model should not only update event-by-event. diff --git a/docs/research/personality-signal-classifier.md b/docs/research/personality-signal-classifier.md index d5c1b01..d32876a 100644 --- a/docs/research/personality-signal-classifier.md +++ b/docs/research/personality-signal-classifier.md @@ -9,6 +9,11 @@ The key design decision is simple: If we skip that split and only model subjective interpretation, the whole system turns into epistemic soup. Nobody shares a reality and every agent becomes a floating bag of projections. +Another key design decision is almost as important: + +- treat concealment, performance, and impression management as part of the signal +- do not assume dialogue is a clean window into the underlying person + ## What Problem This Solves Right now the live Void interaction model mostly works by: @@ -28,6 +33,9 @@ It misses: - sarcasm - mixed motives - meaningful misunderstanding between different listeners +- defensive self-performance +- strategic concealment of traits +- the difference between genuine expression and shell maintenance The next step is not a generic personality classifier. It is a targeted social-signal classifier that predicts the dimensions we actually care about. @@ -50,17 +58,46 @@ all determine what a line is trying to express. That does **not** mean every utterance should be labeled with the speaker's full personality vector. A high-drive, high-anxiety speaker will sometimes say something that expresses neither. The unit of prediction is the **signal expressed in this utterance or event**, not the total soul of the speaker. +It also means that what is expressed may itself be shaped by a defensive mask. + +So the model should not ask only: + +- what does this line reveal + +It should also ask: + +- what does this line conceal +- what identity is being performed +- what kind of injury is being defended against + ## Model Layers ### 1. Speaker State The speaker model should include: +- underlying organization + - self-coherence + - contingent worth + - shame sensitivity + - reciprocity capacity + - mentalization quality + - authenticity tolerance + - mask rigidity - stable dispositions - behavioral dimensions - situational modifiers - active goals - relationship state toward the target +- presentation strategy + - charm + - compliance + - superiority + - detachment + - seductiveness + - competence theater + - moral theater + - cultivated opacity - intended act - reassure - threaten @@ -98,6 +135,18 @@ Targets should be event-level or utterance-level signals such as: - `rigidity` - `withdrawal` +In practice, the canonical reader may need to emit both: + +- expressed interpersonal dimensions +- presentation-style signals + +for example: + +- genuine warmth vs performative warmth +- true withdrawal vs strategic detachment +- organic confidence vs compensatory grandiosity +- actual reciprocity vs manipulative agreeableness + Later additions worth supporting: - `volatility` @@ -145,6 +194,8 @@ This is how you get: That is the good stuff. That is where drama, conflict, and pathos come from. +It is also where agents can fail to see through a mask, or incorrectly think they have seen through one. + ## Void's Special Case Void should not be a literal telepath. @@ -186,6 +237,7 @@ Then label: - canonical expressed dimensions - canonical act strength +- presentation strategy in use - likely listener perceptions for one or more listener profiles ### Important Warning @@ -196,6 +248,7 @@ Train it to infer: - what dimensions are being expressed here - what act is being attempted here +- what presentation strategy is being used here - what a given listener would likely perceive here The hidden personality vector is upstream supervision, not the direct per-line label. @@ -241,7 +294,20 @@ Things like: - apology - gratitude -### C. Listener Perception Labels +### C. Canonical Presentation Labels + +Things like: + +- genuine disclosure +- impression management +- appeasement +- superiority display +- competence theater +- strategic opacity +- moral theater +- shell maintenance under threat + +### D. Listener Perception Labels For each selected listener profile: @@ -254,7 +320,7 @@ For each selected listener profile: - perceived flirtation or intimacy bid - perceived disrespect -### D. Error Labels +### E. Error Labels It is useful to mark where the listener is wrong: @@ -264,6 +330,8 @@ It is useful to mark where the listener is wrong: - hostile attribution error - false reassurance read - false contempt read +- failed mask detection +- false mask attribution That makes misunderstanding legible instead of magical. @@ -294,6 +362,7 @@ Use a hybrid: - heuristics for explicit hard edges - classifier for softer dimensions +- classifier or heuristics for overt presentation strategies when they are obvious - aggregation layer for profile updates - listener perception layer for agent-specific misreading @@ -318,6 +387,8 @@ One brutal betrayal should matter fast. One odd line should not convince the system that somebody is now permanently grandiose, avoidant, or in love. +Likewise, one polished or ingratiating line should not convince the system that a performed self is the whole person. + ## Evaluation We should test three separate things. @@ -369,6 +440,14 @@ That means Aetheria populations can be modeled as: This is a far better fit than asking whether a colony is "high in extraversion" and pretending that captures how it responds to scarcity, humiliation, media pressure, and prestige markets. +It is also a better fit for modeling institutions that train presentation itself: + +- prestige cultures +- fear states +- audit-heavy regimes +- influencer or media ecologies +- environments where people survive by performing the correct self + ## Near-Term Implementation Path 1. Keep the current heuristic pipeline as the hard-edge fallback. @@ -401,6 +480,7 @@ The right shape is: - hidden speaker state - generated utterance - canonical social-signal read +- canonical presentation-style read - listener-biased perception of that signal - profile updates based on repeated evidence diff --git a/state/evidence.jsonl b/state/evidence.jsonl index f82a625..037f992 100644 --- a/state/evidence.jsonl +++ b/state/evidence.jsonl @@ -12,3 +12,4 @@ {"ts":"2026-05-01T15:39:41Z","type":"architecture","status":"ok","note":"The local Ollama lane and worker MCP surface were split into orchestration, helper, and shared modules; the obvious runtime-file monarchies are gone enough that further seam cuts are now elective rather than the next priority by default."} {"ts":"2026-05-01T16:13:06Z","type":"research","status":"ok","note":"Persisted a focused personality-model roadmap: the current Void behavioral-dimension stack is a better basis for future agent and population modeling than the older Big Five colony layer, and the next worthwhile additions are volatility, attachment-vs-distance, reflection, and a split between social stance and project-thinking style."} {"ts":"2026-05-01T16:27:17Z","type":"research","status":"ok","note":"Persisted the personality-signal classifier design: generated dialogue should be read through a canonical event-level classifier and then distorted per listener by EQ, personality, relationship baggage, and situational load. The utterance is not the ground truth; the hidden speaker state and expressed signal are."} +{"ts":"2026-05-01T16:47:54Z","type":"research","status":"ok","note":"Expanded the personality roadmap and classifier spec to treat performed selves, contingent-worth defenses, and impression management as first-class structure. Dialogue is not a clean window into the person; concealment and shell-maintenance are themselves part of the signal the system should model."}