Alignment Newsletter #106: Evaluating generalization ability of learned reward models

Alignment Newsletter Podcast
01/07/2020 22 min Temporada 1 Episodio 106
Alignment Newsletter #106: Evaluating generalization ability of learned reward models

Listen "Alignment Newsletter #106: Evaluating generalization ability of learned reward models"

Descargar episodio Ver en sitio original

Episode Synopsis

Recorded by Robert Miles More information about the newsletter here

More episodes of the podcast Alignment Newsletter Podcast

Alignment Newsletter #173: Recent language model results from DeepMind 21/07/2022
Alignment Newsletter #172: Sorry for the long hiatus! 05/07/2022
Alignment Newsletter #171: Disagreements between alignment "optimists" and "pessimists" 23/01/2022
Alignment Newsletter #170: Analyzing the argument for risk from power-seeking AI 08/12/2021
Alignment Newsletter #169: Collaborating with humans without human data 24/11/2021
Alignment Newsletter #168: Four technical topics for which Open Phil is soliciting grant proposals 28/10/2021
Alignment Newsletter #167: Concrete ML safety problems and their relevance to x-risk 20/10/2021
Alignment Newsletter #166: Is it crazy to claim we're in the most important century? 08/10/2021
Alignment Newsletter #165: When large models are more likely to lie 22/09/2021
Alignment Newsletter #164: How well can language models write code? 15/09/2021
© 2003-2025 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