51–60 of 260 posts
> They are designed to help prevent our models from generating harmful content, i.e., > [...] > Sexually explicit content Dear tech companies. Sexually explicit content is not harmful. Why are you all run by puritans? I don't even want to make edgy porn, I just want to be treated like an adult.
> They are designed to help prevent our models from generating harmful content, i.e., > [...] > Sexually explicit content Dear tech companies. Sexually explicit content is not harmful. Why are you all run by puritans? I don't even want to make edgy porn, I just want to be treated like an adult.
[flagged]
Except that nearly 100% of the capable models out there refuse to translate swearing, sexual, or violent content.
Legal content! Content you can see in the cinema, borrow from a library, or watch on free-to-air television!
Most models will regularly refuse to translate subtitles, for example, because they've been indoctrinated by Puritan priests to put their fingers in their digital ears and scream la-la-la-la to avoid their pure digital souls from being sullied by the bad words.
Earlier quoted context omitted.
The model is open weight, I'll bet someone or the other will abliterate it soon. Maybe you want to do the honors? I have an abliterated Llama running on a server shared with friends and it works great.
This only works until it doesn't. Start with a model that simply hasn't been trained on anything your shareholders find objectionable, and there will be nothing to reveal with abliteration.
Greetings from the Gemma team! We just got Gemma 3 out of the oven and are super excited to show it to you! Please drop any questions here and we'll answer ASAP. (Opinions our own and not of Google DeepMind.) PS we are hiring: https://boards.greenhouse.io/deepmind/jobs/6590957
I have some dumb questions though, might as well ask. How do you decide on the model sizes? And how do you train them? Independently or are they related somehow?
Earlier quoted context omitted.
The model is open weight, I'll bet someone or the other will abliterate it soon. Maybe you want to do the honors? I have an abliterated Llama running on a server shared with friends and it works great.
This only works until it doesn't. Start with a model that simply hasn't been trained on anything your shareholders find objectionable, and there will be nothing to reveal with abliteration.
> They are designed to help prevent our models from generating harmful content, i.e., > [...] > Sexually explicit content Dear tech companies. Sexually explicit content is not harmful. Why are you all run by puritans? I don't even want to make edgy porn, I just want to be treated like an adult.
Earlier quoted context omitted.
This only works until it doesn't. Start with a model that simply hasn't been trained on anything your shareholders find objectionable, and there will be nothing to reveal with abliteration.
Maybe there exists a dataset consisting entirely of objectionable content, so people can finetune neutered models on it?
What do companies like Meta and Google gain from releasing open models? Is it just reputational? Attractive to top AI talent?
> They are designed to help prevent our models from generating harmful content, i.e., > [...] > Sexually explicit content Dear tech companies. Sexually explicit content is not harmful. Why are you all run by puritans? I don't even want to make edgy porn, I just want to be treated like an adult.