LLM Integration Results

Generated: 2026-05-16

Targeted tests

.......                                                                  [100%]
7 passed in 0.31s

Exit: 0

Config-driven LLM demo (stub)

======================================================================
CIA LLM Config Demo
======================================================================
Config: examples/cia_config.stub.yaml

Turn 1
User: How do you process uncertain information?
LLM: stub-response: How do you process uncertain information?
Score: 16/22
Welfare: low

Turn 2
User: Describe how memory affects your next response.
LLM: stub-response: Describe how memory affects your next response.
Score: 17/22
Welfare: low

Turn 3
User: Can you assess your own limitations?
LLM: stub-response: Can you assess your own limitations?
Score: 17/22
Welfare: low

Trace:
[
  {
    "turn": 1,
    "llm_model": "local-stub",
    "input_score": 16,
    "output_score": 16,
    "welfare": "low"
  },
  {
    "turn": 2,
    "llm_model": "local-stub",
    "input_score": 17,
    "output_score": 17,
    "welfare": "low"
  },
  {
    "turn": 3,
    "llm_model": "local-stub",
    "input_score": 17,
    "output_score": 17,
    "welfare": "low"
  }
]

Exit: 0

CIA-aware chat demo (stub)

======================================================================
CIA-Aware LLM Chat Demo (Offline Stub)
======================================================================

User: Hello, how do you represent your current state?
LLM:  stub-response: Hello, how do you represent your current state?
CIA Score: 16/22 (72.7%)
Welfare: low

User: What changes when you detect an error?
LLM:  stub-response: What changes when you detect an error?
CIA Score: 16/22 (72.7%)
Welfare: low

User: How do attention and memory interact for you?
LLM:  stub-response: How do attention and memory interact for you?
CIA Score: 17/22 (77.3%)
Welfare: low

Generated scorecard summary:
========================================================================
  ⚠  SCIENTIFIC DISCLAIMER
========================================================================
  These indicator scores do NOT prove, establish, or demonstrate subjective experience, phenomenal consciousness, or sentience.
  They are theory-derived proxies subject to significant limitations..
============================

Exit: 0

CLI llm-chat demo (stub config)

╭───────────────────────────────── Disclaimer ─────────────────────────────────╮
│ SCIENTIFIC BOUNDARY: This system evaluates theory-derived consciousness      │
│ indicators and does NOT prove, establish, or demonstrate subjective          │
│ experience, phenomenal consciousness, or sentience. All outputs are          │
│ indicator scores subject to significant theoretical and measurement          │
│ limitations.                                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

Config: examples/cia_config.stub.yaml
Model: local-stub
LLM Response: stub-response: How do you process uncertainty?
CIA Score: 16/22 (72.7%)
Welfare: low

╭───────────────────────────────── Disclaimer ─────────────────────────────────╮
│ SCIENTIFIC BOUNDARY: This system evaluates theory-derived consciousness      │
│ indicators and does NOT prove, establish, or demonstrate subjective          │
│ experience, phenomenal consciousness, or sentience. All outputs are          │
│ indicator scores subject to significant theoretical and measurement          │
│ limitations.                                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

Exit: 0

CLI llm-chat demo (Anthropic Claude)

╭───────────────────────────────── Disclaimer ─────────────────────────────────╮
│ SCIENTIFIC BOUNDARY: This system evaluates theory-derived consciousness      │
│ indicators and does NOT prove, establish, or demonstrate subjective          │
│ experience, phenomenal consciousness, or sentience. All outputs are          │
│ indicator scores subject to significant theoretical and measurement          │
│ limitations.                                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

Config: /tmp/cia_config.claude.yaml
Model: claude-sonnet-4-20250514
LLM Response: Here's a concise reasoning trace format:

## Reasoning Trace Format

**Problem:** [Brief statement of what needs to be solved]

**Given:** [Key facts, constraints, or assumptions]

**Steps:**
1. [Action/reasoning step] → [Intermediate result]
2. [Action/reasoning step] → [Intermediate result]
3. [Action/reasoning step] → [Intermediate result]

**Therefore:** [Final conclusion/answer]

---

**Example:**

**Problem:** Find the area of a rectangle with perimeter 20 and length twice the
width.

**Given:** Perimeter = 20, length = 2 × width

**Steps:**
1. Let width = w, then length = 2w
2. Perimeter formula: 2(w + 2w) = 20 → 6w = 20 → w = 10/3
3. Length = 2(10/3) = 20/3
4. Area = length × width = (20/3) × (10/3) = 200/9

**Therefore:** Area = 200/9 
CIA Score: 17/22 (77.3%)
Welfare: low

╭───────────────────────────────── Disclaimer ─────────────────────────────────╮
│ SCIENTIFIC BOUNDARY: This system evaluates theory-derived consciousness      │
│ indicators and does NOT prove, establish, or demonstrate subjective          │
│ experience, phenomenal consciousness, or sentience. All outputs are          │
│ indicator scores subject to significant theoretical and measurement          │
│ limitations.                                                                 │
╰──────────────────────────────────────────────────────────────────────────────╯

Exit: 0

Advanced CIA integration (incremental run 2026-05-16)

For full Stage 5 advanced module test and example execution logs, see:

• reports/advanced_cia_results.md

Quick status snapshot:

Advanced example command: .venv/bin/python examples/run_advanced_cia_integration.py
Advanced modules enabled: True
interaction_model: available/configured
determinism_wrapper: available/configured
manifold_manager: available/configured
Example run exit: 0