Es könnte bald legal sein, KI per Jailbreak aufzudecken, um ihre Funktionsweise offenzulegen
https://www.404media.co/it-may-soon-be-legal-to-jailbreak-ai-to-expose-how-it-works/
Es könnte bald legal sein, KI per Jailbreak aufzudecken, um ihre Funktionsweise offenzulegen
https://www.404media.co/it-may-soon-be-legal-to-jailbreak-ai-to-expose-how-it-works/
6 Kommentare
The U.S. government is currently considering an exemption to U.S. copyright law that would allow people to break technical protection measures and digital rights management (DRM) on AI systems to learn more about how they work, probe them for bias, discrimination, harmful and inaccurate outputs, and to learn more about the data they are trained on. The exemption would allow for “good faith” security and academic research and “red-teaming” of AI products even if the researcher had to circumvent systems designed to prevent that research.
Wouldn’t be surprised to find a bunch of human groups working to make it seem like AI lol. Like Amazon supposedly did.
Reminds me of this Rick and Morty episode https://youtu.be/gTpQ71pgyHQ?si=eFFNEzGonqJX1tFj
„Jailbreak“ AI. WTF. I hate our current vernacular.
Lmfao
90% of what’s called „AI“ is either open sourced or in published academic papers.
There’s no magic, just math. Literally just math.
„Jailbreak“…lmfao
Finally get the ChatGPT jailbreak so we can run doom on it
great now I’m going to have to pull out my trusty „complexity versus interpretability“ chart in internet discussions with people who have no idea what they’re talking about… which I guess isn’t that different from arguing with stakeholders