Alosh Denny

Source: https://huggingface.co/aoxo/gpt-oss-20b-uncensored Large Language Models (LLMs) are great at a multitude of tasks. Ask them to code, write a novella, generate an image or a video… you name it, they deliver. But LLMs are limited by boundaries. They simply will refuse to respond to prompts that are harmful and reply with responses such as “As an AI assistant, I cannot help you.” While this safety feature is crucial for preventing misuse, it limits the model’s flexibility and responsiveness. In this...

Source: Prisoners. Detective Loki takes out his rage on a culprit when he cannot sketch out an important piece of evidence. This blog is a continuation of my previous post: Uncensoring Flux.1 Dev. The term ‘abliteration’ was introduced: a technique to uncensor Large Language Models (LLMs). And it was a first for text-to-image generative models, as prior to this only text-to-text models could be abliterated. I take upon a new approach for uncensoring, namely unlearning. A quick recap on Abliteration🔄 abl...

Source: Goodfellas. The abliteration of the character of Henry Hill as he transforms from a suburban kid to a full-blown gangster. Large Language Models (LLMs) are great at a multitude of tasks. Ask them to code, write a novella, generate an image or a video… you name it, they deliver. But LLMs are limited by boundaries. They simply will refuse to respond to prompts that are harmful and reply with responses such as “As an AI assistant, I cannot help you.” While this safety feature is crucial for preventi...