Alignment Newsletter Podcast
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/
- Update frequency
- every 7 days
- Average duration
- 16 minutes
- Episodes
- 100
- Years Active
- 2019 - 2022
Alignment Newsletter #133: Building machines that can cooperate (with humans, institutions, or other machines)
Recorded by Robert Miles: http://robertskmiles.com
More information about the newsletter here: https://rohinshah.com/alignment-newsletter/
YouTube Channel: https://www.youtube.com/channel/UCfGGFXwKpr…
00:17:12 |
Wed 13 Jan 2021
Alignment Newsletter #132: Complex and subtly incorrect arguments as an obstacle to debate
Recorded by Robert Miles: http://robertskmiles.com
More information about the newsletter here: https://rohinshah.com/alignment-newsletter/
YouTube Channel: https://www.youtube.com/channel/UCfGGFXwKpr…
00:17:44 |
Wed 06 Jan 2021
Alignment Newsletter #131: Formalizing the argument of ignored attributes in a utility function
00:17:06 |
Thu 31 Dec 2020
Alignment Newsletter #130: A new AI x-risk podcast, and reviews of the field
00:12:08 |
Thu 24 Dec 2020
Alignment Newsletter #129: Explaining double descent by measuring bias and variance
00:13:11 |
Thu 17 Dec 2020
Alignment Newsletter #128: Prioritizing research on AI existential safety based on its application to governance demands
00:18:30 |
Wed 09 Dec 2020
Alignment Newsletter #127: Rethinking agency: Cartesian frames as a formalization of ways to carve up the world into an agent and its environment
00:22:56 |
Wed 02 Dec 2020
Alignment Newsletter #126: Avoiding wireheading by decoupling action feedback from action effects
00:16:59 |
Thu 26 Nov 2020
Alignment Newsletter #125: Neural network scaling laws across multiple modalities
00:14:41 |
Wed 11 Nov 2020
Alignment Newsletter #123: Inferring what is valuable in order to align recommender systems
00:14:59 |
Wed 28 Oct 2020
Alignment Newsletter #122: Arguing for AGI-driven existential risk from first principles
00:15:39 |
Wed 21 Oct 2020
Alignment Newsletter #121: Forecasting transformative AI timelines using biological anchors
00:26:39 |
Wed 14 Oct 2020
Alignment Newsletter #120: Tracing the intellectual roots of AI and AI alignment
00:17:32 |
Wed 07 Oct 2020
Alignment Newsletter #119: AI safety when agents are shaped by environments, not rewards
00:21:33 |
Wed 30 Sep 2020
Alignment Newsletter #118: Risks, solutions, and prioritization in a world with many AI systems
00:19:47 |
Wed 23 Sep 2020
Alignment Newsletter #117: How neural nets would fare under the TEVV framework
00:14:03 |
Wed 16 Sep 2020
Alignment Newsletter #116: How to make explanations of neurons compositional
00:17:54 |
Wed 09 Sep 2020
Alignment Newsletter #115: AI safety research problems in the AI-GA framework
00:12:31 |
Wed 02 Sep 2020
Alignment Newsletter #114: Theory-inspired safety solutions for powerful Bayesian RL agents
00:15:12 |
Wed 26 Aug 2020
Disclaimer: The podcast and artwork embedded on this page are the property of Robert Miles. This content is not affiliated with or endorsed by eachpod.com.