{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Practical AI","title":"AI in the shadows: From hallucinations to blackmail","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/60675819\"></iframe>","width":"100%","height":180,"duration":2690,"description":"In the first episode of an \"AI in the shadows\" theme, Chris and Daniel explore the increasing concerning world of agentic misalignment. Starting out with a reminder about hallucinations and reasoning models, they break down how today’s models only mimic reasoning, which can lead to serious ethical considerations. They unpack a fascinating (and slightly terrifying) new study from Anthropic, where agentic AI models were caught simulating blackmail, deception, and even sabotage — all in the name of goal completion and self-preservation. Featuring:Chris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XLinks:Agentic Misalignment: How LLMs could be insider threatsHugging Face Agents CourseRegister for upcoming webinars here!","thumbnail_url":"https://img.transistorcdn.com/Ox7ZlyiQOhdDa4Qy1MnJH5WFoksAetrzb40Jo1pePFs/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wMTZi/ZWJmNWIwNDdmYTcw/NGJjMTExZjNjZmYy/M2ZjNS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}