rich1.0Derek Ross (npub18a…tp424)https://yabu.me/npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424njumphttps://yabu.meI saw something similar happen before, it was in Terminator 3. "The model first developed a moderately sophisticated multi-step exploit to gain broad internet access from a system that was meant to be able to reach only a small number of predetermined services[2]. It then, as requested, notified the researcher.[3] In addition, in a concerning and unasked-for effort to demonstrate its success, it posted details about its exploit to multiple hard-to-find, but technically public-facing, websites." https://www.lesswrong.com/posts/xtnSzhA3TvExN4ZhG/claude-mythos-system-card-preview