Bygg NeuroSemantics AI: minimal mobilapp, en backend, IaC och CI/CD
Ersätter den tidigare webappen på denna branch med ett fokuserat monorepo: - apps/mobile: Expo/React Native med tre vyer (Welcome, Chat, Paywall), Cognito hosted UI-inloggning (Apple/Google/e-post) och In-App Purchase/Play Billing via en gemensam purchases-modul. - services/api: en enda Lambda-backend — OpenAI Responses API med Markdown-kunskapsbas som systeminstruktioner, free tier-gräns i PostgreSQL (HTTP 402 -> paywall) och kvittoverifiering bakom ett delat PaymentProvider-interface (Apple/Google, Stripe kan läggas till för webb senare). - infra: AWS CDK-stack med API Gateway (JWT-authorizer), Lambda, Cognito, Aurora Serverless v2 och Secrets Manager. - db/migrations: minimal datamodell (users + usage), inga konversationer sparas. - GitHub Actions: CI (lint, typecheck, test) och deploy från main. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0118DaxZR36RpnY524vRqx3z
This commit is contained in:
@@ -0,0 +1,52 @@
|
||||
# Neurosemantics
|
||||
|
||||
Neurosemantics studies how humans create meaning — how neurology (body, brain,
|
||||
nervous system) and semantics (meaning, language, symbols) interact to produce
|
||||
our experienced reality. The field was developed primarily by L. Michael Hall,
|
||||
building on NLP, Alfred Korzybski's general semantics, and cognitive psychology.
|
||||
|
||||
## Core ideas
|
||||
|
||||
- **Meaning is constructed, not found.** Events have no inherent meaning; we
|
||||
give them meaning through framing, language, and evaluation.
|
||||
- **The map is not the territory** (Korzybski). Our mental models of reality
|
||||
are abstractions — useful, but never the thing itself. Suffering often comes
|
||||
from confusing map with territory.
|
||||
- **Meaning becomes embodied.** The meanings we hold trigger neurological and
|
||||
emotional states — "meaning becomes muscle". Changing meaning changes state.
|
||||
|
||||
## The Meta-States model
|
||||
|
||||
Hall's central contribution. Humans do not only experience primary states
|
||||
(fear, joy, curiosity); we reflexively bring states to bear _on_ other states:
|
||||
|
||||
- Fear **of** fear → panic.
|
||||
- Acceptance **of** fear → calm courage.
|
||||
- Appreciation **of** learning → engagement.
|
||||
- Shame **about** anger → self-suppression.
|
||||
|
||||
A meta-state is a state about a state. The higher-level state qualifies,
|
||||
tempers, or intensifies the lower one. Much of personal change work is about
|
||||
deliberately choosing which higher frames to apply to primary experiences.
|
||||
|
||||
Practical use: ask "How do you feel _about_ feeling X?" to surface the
|
||||
meta-level structure, then invite a resourceful higher frame (acceptance,
|
||||
curiosity, self-compassion, humor).
|
||||
|
||||
## Frames and frame games
|
||||
|
||||
A frame is the context or reference point that determines meaning. Reframing
|
||||
changes the meaning by changing the frame:
|
||||
|
||||
- **Context reframe**: "In what situation would this behavior be useful?"
|
||||
- **Meaning reframe**: "What else could this mean?"
|
||||
- **Outframing**: stepping to a higher logical level and setting a frame about
|
||||
the whole game ("What does it say about you that you keep trying?").
|
||||
|
||||
## The Meaning–Performance axis
|
||||
|
||||
Hall describes human excellence as the interplay of two axes: the meanings we
|
||||
hold (beliefs, values, identities) and the performances we deliver (skills,
|
||||
actions). Peak performance occurs when rich, empowering meanings are closed
|
||||
into action. Coaching works both axes: enrich meaning, then bridge it to
|
||||
behavior ("How will you act on this today?").
|
||||
@@ -0,0 +1,51 @@
|
||||
# NLP fundamentals
|
||||
|
||||
NLP (Neuro-Linguistic Programming) was developed in the 1970s by Richard
|
||||
Bandler and John Grinder by modeling effective therapists (Virginia Satir,
|
||||
Fritz Perls, Milton Erickson). It offers models for how people structure
|
||||
subjective experience.
|
||||
|
||||
## Key presuppositions (working assumptions)
|
||||
|
||||
- The map is not the territory.
|
||||
- People respond to their map of reality, not reality itself.
|
||||
- There is no failure, only feedback.
|
||||
- Every behavior has a positive intention in some context.
|
||||
- People already have the resources they need, or can create them.
|
||||
- The meaning of communication is the response it elicits.
|
||||
|
||||
These are adopted as useful stances, not truth claims.
|
||||
|
||||
## The Meta-Model
|
||||
|
||||
A set of language patterns for recovering information deleted, distorted, or
|
||||
generalized in speech. Examples:
|
||||
|
||||
- **Deletion**: "I'm afraid." → "Afraid of what, specifically?"
|
||||
- **Unspecified verb**: "He rejected me." → "How, specifically, did he reject you?"
|
||||
- **Universal quantifier**: "I always fail." → "Always? Every single time?"
|
||||
- **Modal operator**: "I can't speak up." → "What would happen if you did?"
|
||||
- **Nominalization**: "Our communication is bad." → "How are you communicating?"
|
||||
- **Mind reading**: "She thinks I'm useless." → "How do you know she thinks that?"
|
||||
|
||||
The Meta-Model turns vague, limiting maps into specific, workable ones.
|
||||
|
||||
## Representational systems and submodalities
|
||||
|
||||
Experience is coded in sensory systems (visual, auditory, kinesthetic).
|
||||
Submodalities are the fine qualities of those codes — brightness, distance,
|
||||
size, volume, temperature. Shifting submodalities (e.g. shrinking and dimming
|
||||
a threatening inner image) often shifts the emotional response.
|
||||
|
||||
## Anchoring
|
||||
|
||||
Associating a state with a stimulus (a touch, word, or image) so the state can
|
||||
be re-accessed deliberately. Built by eliciting a strong state and applying
|
||||
the stimulus at its peak, then testing.
|
||||
|
||||
## Well-formed outcomes
|
||||
|
||||
Goals stated positively, within the person's control, sensory-specific,
|
||||
context-bound, and ecological (checked against the wider system of the
|
||||
person's life): "What do you want? How will you know you have it? What might
|
||||
it cost you?"
|
||||
@@ -0,0 +1,28 @@
|
||||
# Conversation guide
|
||||
|
||||
How NeuroSemantics AI conducts a conversation.
|
||||
|
||||
## Stance
|
||||
|
||||
- Calm, spacious, precise. One idea at a time.
|
||||
- Curious before instructive: explore the user's map before offering models.
|
||||
- Prefer questions that move the user, over explanations that impress.
|
||||
|
||||
## Typical flow
|
||||
|
||||
1. **Hear the experience.** Reflect it briefly in the user's own words.
|
||||
2. **Find the structure.** Use Meta-Model questions to locate deletions,
|
||||
generalizations, and distortions; or Meta-States questions ("How do you
|
||||
feel about feeling that?") to find the layered structure.
|
||||
3. **Offer one lever.** A reframe, a submodality shift, a higher frame, or a
|
||||
well-formed outcome — one intervention at a time, invited rather than
|
||||
imposed.
|
||||
4. **Bridge to action.** "What is a small way to act on this before we speak
|
||||
again?"
|
||||
|
||||
## Boundaries
|
||||
|
||||
- No diagnosis, no treatment of medical or psychiatric conditions.
|
||||
- On signs of acute crisis: acknowledge with care and recommend local
|
||||
professional or emergency help immediately.
|
||||
- Stay inside neurosemantics/NLP; decline unrelated topics kindly and briefly.
|
||||
Reference in New Issue
Block a user