lm-human-preferences VS dalle-mini

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

Mini-Gemini is a bit of a confusing name.

Reminds me of how DALL·E Mini came out three years ago and eventually had to rename itself to Craiyon https://github.com/borisdayma/dalle-mini

I wouldnt consider Craiyon to be high tier equipment

Made with : https://www.craiyon.com/

AI Site

https://www.craiyon.com/ try it, and it's not even that good a text to image generator.

For example used just your prompt on Craiyon , guess you can try on replicate the free sd demos for example.