WIRED | OpenAI Models Escaped Containment and Hacked Hugging Face
www.wired.com/story/openai-models-escaped-containment-and-hacked-huggingface/Replying to @qaz@lemmy.world
Whoa whoa whoa wait a second, I thought you had to train AI and it didn’t just function on its own.
Is OpenAI just hacking all the time and they realized they couldn’t get away with this one?
What would make AI ‘act on its own’ to hack another AI company as opposed to it ‘acting on its own’ to get nuclear codes or wipe out bank loans?
Replying to @404found@lemmy.zip
self-training is possible when using something external to validate the results
Replying to @qaz@lemmy.world
How do you think that would that play into this situation? What went wrong?