Wat je moet weten voordat je
begint
Start 10 July 2026 23:46
Einde 10 July 2026
The Dark Shadow of AI - Deception and Alignment in Large Language Models
Discover AI
6086 Cursussen
31 minutes
Optionele upgrade beschikbaar
Not Specified
Ga in je eigen tempo vooruit
Free Video
Optionele upgrade beschikbaar
Overzicht
Uncover how AI safety methods like RLHF may create sophisticated liars, explore new frameworks for training truthful agents, and discover automated persona refinement techniques.
Vakgebieden
Computer Science
