community-events VS lm-human-preferences

Best applications that will come out of this sprint will receive prizes. You can find more information here. If you want to get started, simply join huggingface.co/discord, take the role 🧨 Diffusers and head to #jax-diffusers-ideas to share your idea or join one of the teams, and fill this form: https://forms.gle/t3M7aNPuLL9V1sfa9

It will start on 17th of April. To join us, you can join huggingface.co/join/discord and take the role Diffusers from #role-assignment. After this, simply fill the form provided in this guide to later get access to TPUs. https://github.com/huggingface/community-events/tree/main/jax-controlnet-sprint

Details and sign-up: https://github.com/huggingface/community-events/tree/main/jax-controlnet-sprint

For the training, I extremely recommend checking out the Whisper Fine-Tuning Event. It has a python script to train in one command, tons of tips, even a walkthrough video.

We are happy to invite you to the Gradio Blocks Party - a community event in which we will create interactive demos for state-of-the-art machine learning models. Demos are powerful because they allow anyone — not just ML engineers — to try out models in the browser, give feedback on predictions, identify trustworthy models. The event will take place from May 17th to 31st. We will be organizing this event on Github and the Hugging Face discord channel. Prizes will be given at the end of the event, see the Prizes section

If you're interested in generative models, Hugging Face is putting on an event around generative models right now called the HugGAN sprint, where they're giving away free access to compute to train models like this.

You can join it by following the steps in the guide here: https://github.com/huggingface/community-events/tree/main/hu...

There will also be talks from awesome folks at EleutherAI, Google, and Deepmind

Lest you think that that sounds like a too galaxy-brained possibility, it has already happened at OpenAI (scroll down to "Bugs can optimize for bad behavior"), just with a model that was very far from being capable enough to be dangerous.

Found relevant code at https://github.com/openai/lm-human-preferences + all code implementations here

That's why, when they're serious, they use RL for finetuning from human preferences (would be hilarious if this attempt to solve the terrible bias you take to be evidence of AGI threat ends up creating a Woke Singleton itself, btw); it's a powerful general approach, and I see no sign of it being applied here.

The kind of measures they are taking, like simply deleting wholesale anything problematic, don't really have a '-1'.

But amusingly, exactly that did happen in one of their GPT experiments! https://openai.com/blog/fine-tuning-gpt-2/

Code for https://arxiv.org/abs/1909.08593 found: https://github.com/openai/lm-human-preferences