))
Alignment Faking: The dark side of LLMs
Manage episode 458305353 series 3463727
Innehåll tillhandahållet av Nyedis. Allt poddinnehåll inklusive avsnitt, grafik och podcastbeskrivningar laddas upp och tillhandahålls direkt av Nyedis eller deras podcastplattformspartner. Om du tror att någon använder ditt upphovsrättsskyddade verk utan din tillåtelse kan du följa processen som beskrivs här https://sv.player.fm/legal.
Recently, Anthropic caught Claude faking alignment. This is going to create a brand new set of issues with AI that we previously did not see happening this quickly. We discuss where AI is headed and what new dangers this will pose.
You can read more about this here: https://www.reddit.com/r/singularity/comments/1hh7w9g/anthropic_caught_claude_faking_alignment_and/
And watch the panel from Anthropic covering this important topic: https://www.youtube.com/watch?v=9eXV64O2Xp8
For full video of this episode, head over to our Youtube channel at http://youtube.com/@nyedisiam
Follow us on your favorite platform for full episodes, shorts, and community feedback:
📺 Linkedin: https://www.linkedin.com/company/77611909/
📷 Instagram: https://www.instagram.com/nyedisiam
🪩 TikTok: https://www.tiktok.com/@nyedisiam
Nyedis Website: https://www.Nyedis.com
233 episoder
Dela
