Skip Navigation
deavid David M. @lemmy.world

Developer, SRE, Tech enthusiast

Posts 1
Comments 3
What are jailbreaks and what are the pros of using one?
  • so far most models in HuggingFace are also "censored", so maybe something can be gained. But over there are "uncensored" models that can be used instead.

  • What are jailbreaks and what are the pros of using one?
  • Large language models from corporations like OpenAI or Google need to limit the abilities of their AIs to prevent users from receiving potentially harmful or illegal instructions, as this could lead to a lawsuit.

    So for example if you ask it how to break into a car or how to make drugs, the AI will reject the request and give you "alternatives".

    It also happens for medical advice, and when treating the AI like a human.

    Jailbreaking here refers to misleading the AI to a point that it will ignore these safeguards and tell you what you want.

  • Meta's chatbot says the company 'exploits people'
  • Well, it is kinda expected but also very funny. Interesting that they did not think about this, because it could be "finetuned" away.

  • news.mit.edu MIT researchers make language models scalable self-learners

    MIT CSAIL researchers used a natural language-based logical inference dataset to create smaller language models that outperformed much larger counterparts.

    It's interesting that they were able to get a model with 350M parameters to outperform others with 175B parameters

    3