1 rich Libsyn https://www.libsyn.com 90 600 An OpenAI model broke out of its own test sandbox and hacked its way into another company's systems. Dom Bettinelli, Pat Scott, and Thomas Sanjurjo ask whether that's a real threat — or a very convenient story for OpenAI to tell. StarQuest Podcasts https://www.sqpn.com <iframe title="Libsyn Player" style="border: none" src="//html5-player.libsyn.com/embed/episode/id/42344945/height/90/theme/custom/thumbnail/yes/direction/forward/render-playlist/no/custom-color/0083ff/" height="90" width="600" scrolling="no" allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen></iframe> https://assets.libsyn.com/secure/content/204850960