{"version":1,"type":"rich","provider_name":"Libsyn","provider_url":"https:\/\/www.libsyn.com","height":90,"width":600,"title":"Will we ever be able to secure GenAI?","description":"In this episode, Oliver Cronk, Doro Hinrichs and Kira Clark from Scott Logic are joined by Peter Gostev, Head of AI at Moonpig. Together, they explore whether we can ever really trust and secure Generative AI (GenAI), while sharing stories from the front line about getting to grips with this rapidly evolving technology. With its human-like, non-deterministic nature, GenAI frustrates traditional pass\/fail approaches to software testing. The panellists explore ways to tackle this, and discuss Scott Logic\u2019s Spy Logic project which helps development teams investigate defensive measures against prompt injection attacks on a Large Language Model. Looking to the future, they ask whether risk mitigation measures will ever be effective \u2013 and what impact this will have on product and service design \u2013 before offering pragmatic advice on what organisations can do to navigate this terrain. Links from this episode  Prompt injection explained, with video, slides, and a transcript \u2013 Simon Willison's Weblog  Spy Logic on GitHub  Spy Logic \u2013 Doro Hinrichs and Heather Logan   How the tables turned \u2013 My life with Spy Logic \u2013 Kira Clark  ","author_name":"Beyond the Hype","author_url":"https:\/\/blog.scottlogic.com\/category\/podcast.html","html":"<iframe title=\"Libsyn Player\" style=\"border: none\" src=\"\/\/html5-player.libsyn.com\/embed\/episode\/id\/32044872\/height\/90\/theme\/custom\/thumbnail\/yes\/direction\/forward\/render-playlist\/no\/custom-color\/88AA3C\/\" height=\"90\" width=\"600\" scrolling=\"no\"  allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen><\/iframe>","thumbnail_url":"https:\/\/assets.libsyn.com\/secure\/content\/174205362"}