/clewd

Primary LanguageJavaScript

Clewd

Clewd

doom & coom

Warning: Some accounts are getting hard-censored by the rats, you might notice it



CHANGELOG

Requirements

Defaults

SettingName: (DEFAULT)/opt1/opt2...

  • Superfetch: (true)/false

    • true will use an alternate method to get past the We are unable to serve your request error
    • false won't use this method and you may get the error again

  • PreventImperson: (true)/false

    • true trims the bot reply immediately if he says "Human:", "Assistant:", "H:" or "A:"
    • making it so it doesn't hallucinate speaking as you (chance of missing some spicy things)

  • PromptExperiments: (true)/false

    • true is an alternative way to send your prompt to the AI
    • experiment before setting to false
    • incompatible with RenewAlways set to false

  • RetryRegenerate: (false)/true

    • true uses the AI's own retry mechanism when you regenerate on your frontend
    • instead of a new conversation
    • experiment with it

  • SystemExperiments: (true)/false

    • only has any effect when RenewAlways is false
    • true alternates between Main+Jailbreak+User and Jailbreak+User
    • false doesn't alternate

  • RenewAlways: (true)/false

    • true makes a new conversation context each time
    • false tries to reutilize the same old conversation, sending only the actual last message each time, taking into consideration SystemExperiments (will not work properly unless your Main is the first system prompt and your Jailbreak is the last)

  • StripAssistant: (false)/true

    • true strips the "Assistant:" prefix from the last assistant message (if it's the last message)

  • StripHuman: (false)/true

    • true strips the "Human:" prefix from the last human message (if it's the last message)

  • AllSamples: (false)/true

    • mutually exclusive with NoSamples
    • true converts all real dialogues to "sample dialogues" (except the last Assistant and Human messages)
    • you're "H" and the AI is "A"
    • whatever the AI replies with is kept (only outgoing)
    • see this for more information
    • Human->H
    • Assistant->A

  • NoSamples: (false)/true

    • mutually exclusive with AllSamples
    • true converts all "sample dialogues" to real dialogues
    • you're "Human" and the AI is "Assistant"
    • whatever the AI replies with is kept (only outgoing)
    • see this for more information
    • H->Human
    • A->Assistant

  • LogMessages: (false)/true

    • true logs prompt and reply to log.txt

  • ClearFlags: (false)/true

    • possibly snake-oil
    • clears your warnings

  • PassParams: (false)/true

    • true will send the temperature you set on your frontend
    • only values under <=1.0 >= 0.1
    • this could get your account banned
    • if clewd stops working, set to false

  • PreserveChats: (false)/true

    • true prevents the deletion of old chats at any point

Examples

safe setup

PreventImperson: true

RenewAlways: true

PromptExperiments: true

PreserveChats: true

experimental setup

SystemExperiments: true

RetryRegenerate: true

PreventImperson: true

RenewAlways: false

PromptExperiments: false

AllSamples: true

Contact

Downloads

Download latest version

Download 3.8.5

Download 2.7