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
- 153NEW
- 189Decreased by 115
- 135NEW
- 138Decreased by 58
- 196Increased by 0
Episódios recentes
![](https://files.podcastos.com/shows/prv3qt/jpeg256-3baeb02e.jpg)
Jan 2, 2025
We Need a Science of Evals
20 mins
![](https://files.podcastos.com/shows/prv3qt/jpeg256-3baeb02e.jpg)
Jan 2, 2025
Introduction to Mechanistic Interpretability
12 mins
![](https://files.podcastos.com/shows/prv3qt/jpeg256-3baeb02e.jpg)
Jul 19, 2024
Illustrating Reinforcement Learning from Human Feedback (RLHF)
S3 E2 • 23 mins
![](https://files.podcastos.com/shows/prv3qt/jpeg256-3baeb02e.jpg)
Jul 19, 2024
Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
S3 E4 • 32 mins
![](https://files.podcastos.com/shows/prv3qt/jpeg256-3baeb02e.jpg)
Jul 19, 2024
Constitutional AI Harmlessness from AI Feedback
S3 E2 • 62 mins
![](https://files.podcastos.com/shows/prv3qt/jpeg-b5168849.jpg)
Idioma
Inglês
País
Reino Unido
Feed Host
Website
Feed
Solicitar uma atualização
As atualizações podem levar alguns minutos.