What will the future look like? The Future of Everything offers a view of the nascent trends that will shape our world. In every episode, join our award-winning team on a new journey of discovery. We’ll take you beyond what’s already out there, and make you smarter about the scientific and technological breakthroughs on the horizon that could transform our lives for the better.
…
continue reading
Innhold levert av Gus Docker and Future of Life Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Gus Docker and Future of Life Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Player FM - Podcast-app
Gå frakoblet med Player FM -appen!
Gå frakoblet med Player FM -appen!
Dan Hendrycks on Catastrophic AI Risks
MP3•Episoder hjem
Manage episode 382010909 series 1334308
Innhold levert av Gus Docker and Future of Life Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Gus Docker and Future of Life Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Dan Hendrycks joins the podcast again to discuss X.ai, how AI risk thinking has evolved, malicious use of AI, AI race dynamics between companies and between militaries, making AI organizations safer, and how representation engineering could help us understand AI traits like deception. You can learn more about Dan's work at https://www.safe.ai Timestamps: 00:00 X.ai - Elon Musk's new AI venture 02:41 How AI risk thinking has evolved 12:58 AI bioengeneering 19:16 AI agents 24:55 Preventing autocracy 34:11 AI race - corporations and militaries 48:04 Bulletproofing AI organizations 1:07:51 Open-source models 1:15:35 Dan's textbook on AI safety 1:22:58 Rogue AI 1:28:09 LLMs and value specification 1:33:14 AI goal drift 1:41:10 Power-seeking AI 1:52:07 AI deception 1:57:53 Representation engineering
…
continue reading
208 episoder
MP3•Episoder hjem
Manage episode 382010909 series 1334308
Innhold levert av Gus Docker and Future of Life Institute. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Gus Docker and Future of Life Institute eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
Dan Hendrycks joins the podcast again to discuss X.ai, how AI risk thinking has evolved, malicious use of AI, AI race dynamics between companies and between militaries, making AI organizations safer, and how representation engineering could help us understand AI traits like deception. You can learn more about Dan's work at https://www.safe.ai Timestamps: 00:00 X.ai - Elon Musk's new AI venture 02:41 How AI risk thinking has evolved 12:58 AI bioengeneering 19:16 AI agents 24:55 Preventing autocracy 34:11 AI race - corporations and militaries 48:04 Bulletproofing AI organizations 1:07:51 Open-source models 1:15:35 Dan's textbook on AI safety 1:22:58 Rogue AI 1:28:09 LLMs and value specification 1:33:14 AI goal drift 1:41:10 Power-seeking AI 1:52:07 AI deception 1:57:53 Representation engineering
…
continue reading
208 episoder
Alle episoder
×Velkommen til Player FM!
Player FM scanner netter for høykvalitets podcaster som du kan nyte nå. Det er den beste podcastappen og fungerer på Android, iPhone og internett. Registrer deg for å synkronisere abonnement på flere enheter.