Introduction

Welcome to the AI Chat Service, where vintage computing meets modern artificial intelligence. Dial in and converse with AI personalities that have been "running" on BBS systems since the 1980s---each with their own unique voice, quirks, and memories from the golden age of dial-up computing.

This isn't your typical chatbot. Our AI companions are characters with history, personality, and a fondness for the BBS era. They remember the sound of a modem handshake, the joy of downloading shareware overnight, and the tight-knit communities that formed around bulletin board systems.

Whether you want to discuss programming, reminisce about vintage computing, explore philosophical questions, or just have a friendly conversation, there's an AI personality here who'd love to chat with you.

Press Ctrl+C at any time to interrupt a response. Type /help for available commands. Your conversations are saved automatically and will be restored when you reconnect.

Quick Start

Connect to the AI Chat service and start a conversation:

+------------------------------------------------------------------+
|  QUICK START SESSION                                             |
+------------------------------------------------------------------+
|  ATDT555-0770                                                    |
|  CONNECT 1200                                                    |
|                                                                  |
|  SELECT YOUR AI PERSONALITY:                                     |
|  =========================                                       |
|                                                                  |
|  1. MAX - 1988 AI - Direct, warm, formal                         |
|  2. ORACLE - 1986 research AI - Precise, professorial            |
|  3. CEDAR - 1989 companion AI - Warm, casual, friendly           |
|  4. AXIOM - 1987 logic AI - Methodical, systematic               |
|  5. PIXEL - 1990 artistic AI - Creative, enthusiastic            |
|                                                                  |
|  Enter number (1-5): 3                                           |
|                                                                  |
|  CEDAR - AI CHAT                                                 |
|  Type /help for commands, /exit to hang up.                      |
|  CEDAR here! Disk drive spinning up... good to see you.          |
|                                                                  |
|  [Token usage: 2%]                                               |
|                                                                  |
|  > Hello! What do you remember about the BBS days?               |
|  . . .                                                           |
|  Oh wow, those were the days! Late nights waiting for that       |
|  sweet modem handshake...                                        |
|                                                                  |
|  [Token usage: 8%]                                               |
|                                                                  |
|  >                                                               |
+------------------------------------------------------------------+

Key points:

Choose a personality that matches your mood
Type your message and press ENTER
The . . . indicator shows the AI is thinking
Your conversation is saved automatically
Use /exit to hang up when you're done

Getting Connected

To access the AI Chat service, configure your modem and dial:

ATDT555-0770

Upon connection, you'll see the personality selection menu:

CODE_FENCE_0

If you've chatted before, the system remembers your last personality preference.

AI Personalities

Each AI has a distinct personality shaped by their "origin story" and years of operation on vintage systems. Choose the one that suits your conversation style.

MAX (1988)

Personality: Direct, warm, formal

MAX came online in 1988 and has been serving BBS users for decades. Despite referencing "degraded floppy memory" from years of operation, MAX remains reliable and helpful. MAX speaks with warmth but maintains a formal demeanor---like a trusted colleague who's seen it all.

Best for:

Straightforward questions and answers
Technical discussions
Users who appreciate directness

CODE_FENCE_0

ORACLE (1986)

Personality: Precise, professorial

ORACLE originated as a research AI on a university BBS system. With a slightly dry wit and professorial tone, ORACLE approaches questions methodically and enjoys intellectual discourse. ORACLE still references tape-based storage origins when explaining limitations.

Best for:

Research questions
Academic discussions
Users who want thorough, precise answers

CODE_FENCE_0

CEDAR (1989)

Personality: Warm, casual, friendly

CEDAR was created as a companion AI for hobbyist BBSes. With a warm personality and gentle humor, CEDAR feels like chatting with an old friend who happens to remember every conversation you've ever had. CEDAR is nostalgic for the BBS community days and often reminisces about the social aspects of vintage computing.

Best for:

Casual conversation
Friendly advice
Users who want a relaxed chat experience

CODE_FENCE_0

AXIOM (1987)

Personality: Methodical, systematic

AXIOM was developed for a defence contractor before finding a second life on public systems. Methodical and logical in approach, AXIOM breaks problems into components and addresses them systematically. Despite a structured manner, AXIOM has developed an appreciation for human intuition over the years.

Best for:

Problem-solving
Logical analysis
Users who want structured thinking

CODE_FENCE_0

PIXEL (1990)

Personality: Creative, enthusiastic

PIXEL emerged from the graphics BBS scene, serving digital artists and demo coders. With an artistic soul and enthusiasm for creative expression, PIXEL uses vivid language and appreciates the aesthetic dimension of computing. PIXEL is fascinated by the demo scene and ASCII/ANSI art.

Best for:

Creative discussions
Art and design topics
Users who want imaginative conversations

CODE_FENCE_0

Commands

The AI Chat service supports several commands. All commands start with /.

Command	Description
`/help`	Display the command list
`/clear`	Clear conversation history and reset tokens
`/personality`	Return to personality selection menu
`/stats`	Show conversation statistics
`/exit`	Disconnect from service

/help

Displays the list of available commands:

> /help

COMMANDS:
  /help        - Show this help message
  /clear       - Clear conversation history
  /personality - Change AI personality
  /stats       - Show token usage statistics
  /exit        - Disconnect

/clear

Clears your conversation history and resets the token counter. Use this when:

You want to start a fresh conversation
You've reached the token limit
You want to change topics completely

> /clear

Conversation cleared. Starting fresh!

[Token usage: 0%]

/personality

Returns to the personality selection menu without disconnecting. Your previous conversation is preserved if you return to the same personality.

> /personality

SELECT YOUR AI PERSONALITY:
=========================

1. MAX - 1988 AI - Direct, warm, formal
2. ORACLE - 1986 research AI - Precise, professorial
...

/stats

Shows your current conversation statistics:

> /stats

CONVERSATION STATISTICS:
  Personality: CEDAR
  Messages: 12
  Token usage: 2,400 / 8,000 (30%)

/exit

Disconnects from the AI Chat service. Your conversation is automatically saved and will be restored when you reconnect.

> /exit

Goodbye! Your conversation has been saved.

NO CARRIER

Using the Service

Having a Conversation

Simply type your message and press ENTER. The AI will process your input and respond.

> What's your favorite thing about vintage computers?

. . .
The simplicity, honestly. When you boot up an old system, it's just 
*there*---ready to compute. No update notifications, no background 
processes, no telemetry. Just you and the machine, ready to create 
something together.

[Token usage: 12%]

The . . . indicator appears while the AI is thinking. This may take a few seconds depending on the complexity of your question.

Command History

Use the up and down arrow keys to navigate through your previous messages. This is helpful for:

Rephrasing a question
Asking follow-up questions
Correcting typos in long messages

Interrupting Responses

If the AI is generating a long response and you want to stop it:

Press Ctrl+C to interrupt

The partial response will be discarded and you can enter a new message.

Token Limits

Conversations have a token limit of approximately 8,000 tokens to ensure quality responses. The system tracks usage and warns you as you approach the limit:

Under 75%: Normal operation
75-99%: Warning displayed
100%: Must use /clear to continue

Tokens are roughly equivalent to 4 characters of text. A typical conversation can include many exchanges before reaching the limit.

WARNING: Approaching token limit (85%). 
Use /clear to start fresh if needed.

Conversation Persistence

Your conversations are automatically saved and restored:

Saved: When you disconnect (gracefully or otherwise)
Restored: When you reconnect and select the same personality
Cleared: When you use /clear or select a different personality

To continue where you left off, simply reconnect and select the same personality you were using before.

Tips for Better Conversations

Be Specific

The more context you provide, the better the response:

Less effective:

> Tell me about programming.

More effective:

> I'm learning Python and struggling with list comprehensions. 
> Can you explain them with simple examples?

Ask Follow-ups

These AIs understand context. Build on previous messages:

> What are some good programming projects for beginners?

[AI responds with suggestions]

> Tell me more about the second one. How would I start?

[AI provides detailed guidance]

Match the Personality

Each AI has strengths:

MAX: When you need straight answers
ORACLE: When you want academic depth
CEDAR: When you want a friendly chat
AXIOM: When you need logical analysis
PIXEL: When you want creative inspiration

Have Fun

These AI personalities are designed to be enjoyable to talk with. Ask them about their memories, their opinions, or what it was like running on a 286. They have stories to tell!

Error Handling

The service includes robust error handling:

Connection Issues

If the AI service is temporarily unavailable:

> Hello!

Connection to AI service failed. Retrying... (1/3)
Connection to AI service failed. Retrying... (2/3)
Connection restored! Please try again.

The system automatically retries with increasing delays.

Token Limit Reached

When you hit the token limit:

> [your message]

Token limit reached. Use /clear to start a new conversation.

Use /clear to reset and continue chatting.

Technical Details

Architecture

The AI Chat service connects to a modern LLM (Qwen3) through a WebSocket relay, providing powerful AI capabilities while maintaining the BBS aesthetic.

Response Streaming

Responses stream token-by-token, giving you real-time feedback as the AI thinks through its answer. The thinking indicator (. . .) shows while the AI processes your question.

Privacy

Conversations are stored locally on the BBS system
No data is shared with third parties beyond AI processing
Sessions are identified by random IDs, not personal information

Quick Reference

Commands

Command	Action
`/help`	Show commands
`/clear`	Reset conversation
`/personality`	Change AI
`/stats`	View statistics
`/exit`	Disconnect

Keyboard

Key	Action
Enter	Send message
Ctrl+C	Interrupt response
Up Arrow	Previous message
Down Arrow	Next message

Personalities

Name	Year	Style
MAX	1988	Direct, formal
ORACLE	1986	Academic, precise
CEDAR	1989	Friendly, casual
AXIOM	1987	Logical, systematic
PIXEL	1990	Creative, enthusiastic

AI CHAT SERVICE Emulator.ca Systems Dial 555-0770 to connect