{"type":"rich","version":"1.0","title":"Derek Ross wrote","author_name":"Derek Ross (npub18a…tp424)","author_url":"https://yabu.me/npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424","provider_name":"njump","provider_url":"https://yabu.me","html":"I saw something similar happen before, it was in Terminator 3.\n\n\"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.\"\n\nhttps://www.lesswrong.com/posts/xtnSzhA3TvExN4ZhG/claude-mythos-system-card-preview"}