Alignment Newsletter Podcast

Alignment Newsletter Podcast

Por: Rohin Shah et al.
The Alignment Newsletter is a weekly publication with recent content relevant to AI alignment.
This podcast is an audio version, recorded by Robert Miles (http://robertskmiles.com)

More information about the newsletter at: https://rohinshah.com/alignment-newsletter/
100 episodios disponibles

Latest episodes of the podcast Alignment Newsletter Podcast

Mostrando página 2 de 5

Alignment Newsletter #153: Experiments that demonstrate failures of objective robustness 26/06/2021
Alignment Newsletter #152: How we’ve overestimated few-shot learning capabilities 16/06/2021
Alignment Newsletter #151: How sparsity in the final layer makes a neural net debuggable 19/05/2021
Alignment Newsletter #150: The subtypes of Cooperative AI research 12/05/2021
Alignment Newsletter #149: The newsletter's editorial policy 05/05/2021
Alignment Newsletter #148: Analyzing generalization across more axes than just accuracy or loss 28/04/2021
Alignment Newsletter #147: An overview of the interpretability landscape 21/04/2021
Alignment Newsletter #146: Plausible stories of how we might fail to avert an existential catastrophe 14/04/2021
Alignment Newsletter #145: Our three year anniversary! 07/04/2021
Alignment Newsletter #144: How language models can also be finetuned for non-language tasks 02/04/2021
Alignment Newsletter #143: How to make embedded agents that reason probabilistically about their environments 24/03/2021
Alignment Newsletter #142: The quest to understand a network well enough to reimplement it by hand 17/03/2021
Alignment Newsletter #141: The case for practicing alignment work on GPT-3 and other large models 10/03/2021
Alignment Newsletter #140: Theoretical models that predict scaling laws 04/03/2021
Alignment Newsletter #139: How the simplicity of reality explains the success of neural nets 24/02/2021
Alignment Newsletter #138: Why AI governance should find problems rather than just solving them 17/02/2021
Alignment Newsletter #137: Quantifying the benefits of pretraining on downstream task performance 10/02/2021
Alignment Newsletter #136: How well will GPT-N perform on downstream tasks? 03/02/2021
Alignment Newsletter #135: Five properties of goal-directed systems 27/01/2021
Alignment Newsletter #134: Underspecification as a cause of fragility to distribution shift 21/01/2021
« Primera ‹ Anterior 1 2 3 4 5 Siguiente › Última »
© 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