Explore recursos valiosos do curso Fundamentos de Segurança em IA, oferecendo insights e conhecimentos sobre estratégias de alinhamento para inteligência artificial.
We Need a Science of Evals
20 mins • Jan 2, 2025
Charts
- 185NEW
- 136Decreased by 4
Episódios recentes
Jan 2, 2025
We Need a Science of Evals
20 mins
Jan 2, 2025
Introduction to Mechanistic Interpretability
12 mins
Jul 19, 2024
Illustrating Reinforcement Learning from Human Feedback (RLHF)
S3 E2 • 23 mins
Jul 19, 2024
Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
S3 E4 • 32 mins
Jul 19, 2024
Constitutional AI Harmlessness from AI Feedback
S3 E2 • 62 mins
Idioma
Inglês
País
Vietnã
Feed Host
Website
Feed