Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
Help about MediaWiki
WikiFinn
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Beginner’s Guide to JanitorAi
(section)
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== Key Concepts and Terms === ==== Large Language Model (LLM) ==== A '''Large Language Model''' is an artificial intelligence system trained on vast amounts of text data to understand and generate human-like language. Popular LLMs used on JanitorAI include: * '''OpenAI's GPT-4 and GPT-3.5''' * '''Anthropic’s Claude''' * '''Google Gemini''' * '''DeepSeek and Mixtral''' (open-source alternatives) LLMs are not hosted by JanitorAI. Instead, the platform allows users to connect to these models via third-party APIs or proxies. ==== Tokens ==== A '''token''' is a unit of text processed by an LLM. Tokens typically represent short word fragments, whole words, or punctuation. For example: * "Chatbot" = 1 token * "I love AI!" = 4 tokens LLMs have a '''context window''' that limits how many tokens they can process at once. For instance: * GPT-3.5 has a context window of ~4,096 tokens * GPT-4-Turbo can handle up to ~128,000 tokens If a conversation exceeds the token limit, older messages may be truncated, which can lead to the bot "forgetting" earlier context. ==== Context ==== '''Context''' refers to the visible and hidden chat history the model uses to generate replies. Maintaining relevant context is essential for coherent, ongoing conversations. Some bots and models support "long-term memory," but most rely on short-term context stored during a session. ==== Prompting ==== '''Prompting''' is the method of instructing an LLM by crafting the initial input text. On JanitorAI, prompts can define a bot’s: * Personality and backstory * Response style * Dialogue restrictions or behaviors Effective prompts use a combination of descriptive language and formatting. Some creators use formatting tokens like `{{char}}` and `{{user}}` to reference the bot and user, respectively. ==== API Key ==== An '''API key''' is a string of characters used to authenticate and connect to external AI services. JanitorAI does not provide its own LLMs; instead, users must supply their own API keys from services such as: * [https://platform.openai.com OpenAI] * [https://console.anthropic.com Anthropic Claude] * [https://openrouter.ai OpenRouter] * [https://deepseek.com DeepSeek] Using unofficial or proxy-based APIs may allow access to free models, though reliability and legality can vary. ==== Proxy ==== A '''proxy''' is a service that forwards requests between JanitorAI and an LLM API. Some proxies allow users to avoid rate limits, reduce costs, or use models unavailable via official APIs. Proxies are community-run and should be used with caution, especially when transmitting sensitive information.
Summary:
Please note that all contributions to WikiFinn may be edited, altered, or removed by other contributors. If you do not want your writing to be edited mercilessly, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource (see
WikiFinn:Copyrights
for details).
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)