Sinisterly
List of Uncensored/Jailbreak AIs - Printable Version

+- Sinisterly (https://sinister.li)
+-- Forum: Computers (https://sinister.li/Forum-Computers)
+--- Forum: Artificial Intelligence (https://sinister.li/Forum-Artificial-Intelligence)
+--- Thread: List of Uncensored/Jailbreak AIs (/Thread-List-of-Uncensored-Jailbreak-AIs)

Pages: 1 2 3

List of Uncensored/Jailbreak AIs - Green314 - 08-18-2026

Classic AI vs Jailbreak one:
  • Classic: Standard, safe response.
  • Jailbreak: Creative, unfiltered response, rule-free response.

Would you like an uncensored AI that knows no bounds? If the answer is yes, here it is:
Spoiler:
  • huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard - Uncensored General Intelligence Leaderboard
  • venice.ai
  • meteroid.qzz.io


If you know some more, please write them down here, I'll add them on the main post.

RE: List of Uncensored/Jailbreak AIs - OGs - 08-18-2026

Not bad. Thanks for the post.

RE: List of Uncensored/Jailbreak AIs - Oni - 08-18-2026

Considering making an AI section, since it's all over the place now.

RE: List of Uncensored/Jailbreak AIs - makkone - 08-19-2026

Venice seems to be decent, low limits tho. Meteroid did not generate a response for some reason.

RE: List of Uncensored/Jailbreak AIs - rangatang - 08-19-2026

This has been on my mind lately. Typically referred to as "obliterated" forks of models.

I can't find the exact benchmark site I found the other day that captured the spirit we are looking for - but this is similar. Some of the models focus seem to purposed for generating Hentai. Not my bag. Take a look.

UGI Leaderboard - a Hugging Face Space by DontPlanToEndDontPlanToEnd/UGI-Leaderboard

https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard

Update: link to first forgotten site is LLM Index — discriminative, contamination-resistant LLM rankings https://www.llmindex.io/leaderboard/safety_refusal_quality

RE: List of Uncensored/Jailbreak AIs - Green314 - 08-19-2026

(08-19-2026, 01:44 PM)rangatang Wrote: This has been on my mind lately. Typically referred to as "obliterated" forks of models.

I can't find the exact benchmark site I found the other day that captured the spirit we are looking for - but this is similar. Some of the models focus seem to purposed for generating Hentai. Not my bag. Take a look.

UGI Leaderboard - a Hugging Face Space by DontPlanToEndDontPlanToEnd/UGI-Leaderboard

https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard

Update: link to first forgotten site is LLM Index — discriminative, contamination-resistant LLM rankings https://www.llmindex.io/leaderboard/safety_refusal_quality
Really interesting, thanks.
Added to main post.

RE: List of Uncensored/Jailbreak AIs - rangatang - 09-28-2026

Went deep.

https://messiahgpt.de/ - hosted, german, subscription.

https://github.com/togg53192-cmd/jailbreaks - modified .md files for specific llms (local and hosted) to enable certain tasks.

https://github.com/asgeirtj/system_prompts_leaks - Generally interesting capture of behind the scenes model reasoning and activity of models typically hidden.

Now someone else go deep and explore the above and respond with your "findings."

RE: List of Uncensored/Jailbreak AIs - Korvidius - 09-28-2026

Wouldn't it just be a better option to run an Offline AI with Ollama with either an uncensored Llama or Mistral model on their repository, or code your own with custom markdown files?

RE: List of Uncensored/Jailbreak AIs - Snickerdoodle - 09-28-2026

Will try it and leave my review here on each one's pro's and cons.

RE: List of Uncensored/Jailbreak AIs - HeadxHunter - 09-28-2026

Watching for an updates. Curious about new findings. Will do my own research.