Dylan Hadfield-Menell, UC Berkeley/MIT: The value alignment problem in AI

Generally Intelligent
12/05/2021 1h 31min

Listen "Dylan Hadfield-Menell, UC Berkeley/MIT: The value alignment problem in AI"

Descargar episodio Ver en sitio original

Episode Synopsis

Dylan Hadfield-Menell (Google Scholar) (Website) recently finished his PhD at UC Berkeley and is starting as an assistant professor at MIT. He works on the problem of designing AI algorithms that pursue the intended goal of their users, designers, and society in general.  This is known as the value alignment problem.Highlights from our conversation:👨‍👩‍👧‍👦 How to align AI to human values📉 Consequences of misaligned AI -> bias & misdirected optimization📱 Better AI recommender systems

More episodes of the podcast Generally Intelligent

Malleable software and human agency with Geoffrey Litt 14/11/2025
From lawless spaces to true liberty: rethinking AI's role in society 13/08/2025
Rylan Schaeffer, Stanford: Investigating emergent abilities and challenging dominant research ideas 18/09/2024
Ari Morcos, DatologyAI: Leveraging data to democratize model training 11/07/2024
Percy Liang, Stanford: The paradigm shift and societal effects of foundation models 09/05/2024
Seth Lazar, Australian National University: Legitimate power, moral nuance, and the political philosophy of AI 12/03/2024
Tri Dao, Stanford: FlashAttention and sparsity, quantization, and efficient inference 09/08/2023
Jamie Simon, UC Berkeley: Theoretical principles for how neural networks learn and generalize 22/06/2023
Bill Thompson, UC Berkeley: How cultural evolution shapes knowledge acquisition 29/03/2023
Ben Eysenbach, CMU: Designing simpler and more principled RL algorithms 23/03/2023
© 2003-2026 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA