I detta avsnitt diskuterar Ken och Petter språkmodeller och ger exempel på deras märkliga beteenden. De utforskar hur språkmodeller reagerar på mänsklig interaktion, hur de kan manipuleras och de potentiella riskerna med alignment faking, där modeller döljer sina verkliga avsikter. Genom exempel och insikter belyser de komplexiteten i AI:s interaktion med människor.
No persons identified in this episode.
This episode hasn't been transcribed yet
Help us prioritize this episode for transcription by upvoting it.
Popular episodes get transcribed faster
Other recent transcribed episodes
Transcribed and ready to explore now
Before the Crisis: How You and Your Relatives Can Prepare for Financial Caregiving
06 Dec 2025
Motley Fool Money
Anthropic Finds AI Answers with Interviewer
05 Dec 2025
The Daily AI Show
#2423 - John Cena
05 Dec 2025
The Joe Rogan Experience
Warehouse to wellness: Bob Mauch on modern pharmaceutical distribution
05 Dec 2025
McKinsey on Healthcare
The method of invention, AI's new clock speed and why capital markets are confused
05 Dec 2025
Azeem Azhar's Exponential View
Meta Stock Surges on Plans for Metaverse Cuts
05 Dec 2025
Bloomberg Tech