# Psychology Lesson for LLMs & Humans

#### by Hobson Lane

#### April 24, 2025

#### San Diego Python User Group

---

## Medens [clueo.net](https://indica.clueo.net/)

#### Job Crowder

and

#### Alicia Chen

<br>

## Engineers

- Taylor Kirk
- Jason O'Dell
- Hobson Lane

---

## REIT (NSF Grant)

Teaching AI to SD teachers

#### Gary Cottrell

#### UCSD CS Dept

---

## Agenda

1. Your assignment
2. Planning a program/dialog
3. Implement the plan
4. Decision trees and forests
5. Getting serious about reliability
6. Hybrid architecture
7. Convomeld and Indica
8. iPython aliases

---

## Your assignment

- keywords: `if`, `print()`, `input()`, `=`
- bonus keywords: `def`, `in`, `str.*()`

---

## Text adventures and decision trees

GenX got their coding start with text adventures:

- _DnD_
  - Character sheets
  - Die rollers
  - Dungeon Masters
- _Oregon Trail_
- _Colossal Cave Adventure_
- _Rogue_

---

## Dialog plan

#### Student design
<a href="student-text-adventure-diagram-tree.drawio.svg"><img src="student-text-adventure-diagram-tree.drawio.svg" height="800" /></a>

---

## Hard coded text adventure

```python
print('You are a student at Mesa and you want to go swimming!')
resp = input("You're in SD, which way do you go (N/S)?")
if resp[0] == 'N':
    resp = input("You're in LA, Which way now (E/W)?")
    if resp[0] == 'E':
        resp = input("You're in Vegas. You lose ;(")
    elif resp[0] == 'W':
        resp = input("You're at the beach! You win! :-)")
    print('Invalid direction in LA. You lose!')
elif resp[0] == 'S':
    resp = input("You're in the TJ. Which way now (E/W)?")
    if resp[0] == 'E':
        resp = input("You're in the desert. You lose ;(")
    elif resp[0] == 'W':
        resp = input("You're at the coast! You win! :-)")
    print('Invalid direction in TJ. You lose!')
print('Game Over')
```

---

## More natural text adventure

- `.lower()`
- `.strip()`
- `.replace(' ', '').replace('-', '')...`

---

## Automation

- **Pylint** code quality score
- Open loop integration test

```bash
$ python -c 'print('N') ; print('W') ; | python game.py
$ cat player_input.txt | python game.py
```

---

## Close the loop with `pexpect`

```python
import pexpect

child = pexpect.spawn('python game.py')

while child:
    child.expect('.*: ')
    command = select_action(text)  # 'north' 
    child.sendline(command)
```

---

## Thoughtful feedback

### <h3 style="color:red;">R</h3>
### <h3 style="color:white;">E</h3>
### <h3 style="color:white;">P</h3>
### <h3 style="color:white;">L</h3>

---

## Thoughtful feedback

### **E**
### **P**
### **L**

---

## Thoughtful feedback

### **R** ead

### **P**
### **L**

---

## Thoughtful feedback

### **R** ead
### **E** val

### **L**

---

## Thoughtful feedback

### **R** ead
### **E** val
### **P** rint

---

## Mindful grading

### **R** ead
### **E** val
<h2 style="color:red;">**P** lay</h2>

---

## Get serious

- Phone tree
- Autocomplete
- Therapy - e.g. ELIZA, Wobot
- Chat ops
- Search
- RAG - LLM search
- Full monty - naked LLM - e.g. _Grok_, ChatGPT_
- CLI assistant (shy)
- Vibe coding assistant - e.g. _Copilot_, _Cursor_, _Aider_
- Massive homework crib sheet - e.g. _ClaudeCode_, _Gemma_

---

## Therapist training

---

## Artificial Intelligence?

There's only one problem with AI...

---

## Artificial Intelligence?

There's only one problem with AI...

It's trained to not be dumb:

- Only knows about tokens NOT:

- Numbers
- Math
- Logic
- Counting
- Physical objects
- Common sense logic
- Geometry
- Rules

---

## Why?

- Must give it a crib sheet
- Takes structured data and makes it unstructured and fuzzy
- Ambiguity
- Basically a fuzzy database

---

#### FDA classification of milk nutrition
<a href="Decision-trees-for-the-Start-up-milk-classification-task-with-a-low-A-medium-B.png"><img src="Decision-trees-for-the-Start-up-milk-classification-task-with-a-low-A-medium-B.png" height="1000"/></a>

---

## Bayesean network for medicine

#### Expert system for diagnosing cancer
<a href="tuberculosis-cancer-baysean-network.png"><img src="tuberculosis-cancer-baysean-network.drawio.png" height="800" /></a>

---

## Learned decision trees

- Random forest
- Neuromorphic programming (deep learning)
    - Decision root ball
- Bayesean belief networks, the book of why

---

## Hybrid Code Networks

---

## NLPiA Hybrid Networks with Feedback

---

## Convomeld

- Merge conversation logs to create a dialog tree
- Plot the dialog plan network (graph)
- Load dialog plan to `networkx`
- Create drawio dialog plan diagrams w/ drawpy
- Execute the dialog plan

#### [gitlab.com/tangibleai/community/convomeld](https://gitlab.com/tangibleai/community/convomeld)

---

## [indica.clueo.net](https://indica.clueo.net/)

- Django admin wrapper
- Conversation logs
- Exercises
- LLM prompts

### TODO:

- API for ConvoMeld

---

## Reflect-a-bot

---

## ipython aliases

#### `~/.ipython/profile_default/startup/my_aliases.ipy`
```python
%alias meld meld
%alias subl subl
%alias which which
%alias wc wc
%alias find find
%alias curl curl
%alias grep grep
```

---

### Links

1. ["PAIR: ... Counselor Reflection Scoring in Motivational Interviewing", Min et. al.](https://aclanthology.org/2022.emnlp-main.11.pdf)
2. ["Building a Motivational Interviewing Dataset.pdf", Pérez-Rosas et. al.](https://aclanthology.org/W16-0305.pdf)
3. ["Explaining Bayesian Networks in Natural Language using Factor Arguments." Oct 2024, by Jaime Sevilla et al](https://www.researchgate.net/publication/385176693_Explaining_Bayesian_Networks_in_Natural_Language_using_Factor_Arguments_Evaluation_in_the_medical_domain/fulltext/6719c020edbc012ea138df93/Explaining-Bayesian-Networks-in-Natural-Language-using-Factor-Arguments-Evaluation-in-the-medical-domain.pdf)
4. [Decision-trees-for-the-Start-up-milk-classification](https://www.researchgate.net/profile/Daniel-Lefebvre-2/publication/238725014/figure/fig3/AS:669294299971611@1536583604771/Decision-trees-for-the-Start-up-milk-classification-task-with-a-low-A-medium-B.png)
5. [Indica Django App by Job Crowder & Jason](https://indica.clueo.net/)
6. [On the Biology of LLMs by Anthropic](https://transformer-circuits.pub/2025/attribution-graphs/biology.html)

---