))
When Will AI Models Blackmail You, and Why?
Manage episode 518926536 series 3701080
Inhalt bereitgestellt von Philip - Host of AI Explained YT. Alle Podcast-Inhalte, einschließlich Episoden, Grafiken und Podcast-Beschreibungen, werden direkt von Philip - Host of AI Explained YT oder seinem Podcast-Plattformpartner hochgeladen und bereitgestellt. Wenn Sie glauben, dass jemand Ihr urheberrechtlich geschütztes Werk ohne Ihre Erlaubnis nutzt, können Sie dem hier beschriebenen Verfahren folgen https://de.player.fm/legal.
In the last few days Anthropic have released an impressive honest account of how all models blackmail, no matter what goal they have, and despite prompt warnings, and other preventions. But do these models *want* this?
Thanks to Storyblocks for sponsoring this video! Download unlimited stock media at one set price with Storyblocks: storyblocks.com/AIExplained
AI Insiders ($9!): https://www.patreon.com/AIExplained
Chapters:
00:00 - Introduction
01:20 - What prompts blackmail?
02:44 - Blackmail walkthrough
06:04 - ‘American interests’
08:00 - Inherent desire?
10:45 - Switching Goals
11:35 - Murder
12:22 - Realizing it’s a scenario?
15:02 - Prompt engineering fix?
16:27 - Any fixes?
17:45 - Chekov’s Gun
19:25 - Job implications
21:19 - Bonus Details
Report: https://www.anthropic.com/research/agentic-misalignment
30 Page Appendices: https://assets.anthropic.com/m/6d46dac66e1a132a/original/Agentic_Misalignment_Appendix.pdf
Announcement: https://x.com/AnthropicAI/status/1936144602446082431?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Etweet
OpenAI Files: https://www.openaifiles.org/
Grok 4 News: https://x.com/RonFilipkowski/status/1936372579607912473
Claude 4 Report Card: https://www-cdn.anthropic.com/6be99a52cb68eb70eb9572b4cafad13df32ed995.pdf
New Apollo Research: https://www.apolloresearch.ai/blog/more-capable-models-are-better-at-in-context-scheming
Interesting Reflections: https://nostalgebraist.tumblr.com/post/785766737747574784/the-void
Non-hype Newsletter: https://signaltonoise.beehiiv.com/
41 Episoden
Teilen
