Recent frontier AI hacks show aligned models still caused harm — because alignment measures intent-following, while safety measures graceful failure. They are not the same, and production AI needs…https://www.nerdheadz.com/blog/ai-alignment-vs-safety-frontier-hacks-lessons#ai #machinelearning
Related
As a professional wanker, I’m disappointed that my recruiting email must have gotten caught in a spam filter. (tru)https...
As a professional wanker, I’m disappointed that my recruiting email must have gotten caught in a spam filter. (tru)https://www.wired.com/story/these-masturbation-consultants-were-h...
Confucian Wisdom and #AI Ethics#Technology #AIEthics #China https://m.youtube.com/watch?v=i3Zi19TZM5I&t=61s
Confucian Wisdom and #AI Ethics#Technology #AIEthics #China https://m.youtube.com/watch?v=i3Zi19TZM5I&t=61s
Confucian Wisdom and #AI Ethics#Technology #AIEthics #China m.youtube.com/watch?v=i3Zi...Confucian Wisdom and AI Ethics....
Confucian Wisdom and #AI Ethics#Technology #AIEthics #China m.youtube.com/watch?v=i3Zi...Confucian Wisdom and AI Ethics...