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 #113: Checking the ethical intuitions of large language models
00:17:27 |
Wed 19 Aug 2020
Alignment Newsletter #110: Learning features from human feedback to enable reward learning
00:19:07 |
Wed 29 Jul 2020
Alignment Newsletter #109: Teaching neural nets to generalize the way humans would
00:18:27 |
Wed 22 Jul 2020
Alignment Newsletter #108: Why we should scrutinize arguments for AI risk
00:21:11 |
Wed 15 Jul 2020
Alignment Newsletter #107: The convergent instrumental subgoals of goal-directed agents
00:14:11 |
Thu 09 Jul 2020
Alignment Newsletter #106: Evaluating generalization ability of learned reward models
00:22:17 |
Wed 01 Jul 2020
Alignment Newsletter #105: The economic trajectory of humanity, and what we might mean by optimization
00:20:24 |
Wed 24 Jun 2020
Alignment Newsletter #104: The perils of inaccessible information, and what we can learn about AI alignment from COVID
00:15:40 |
Thu 18 Jun 2020
Alignment Newsletter #103: ARCHES: an agenda for existential safety, and combining natural language with deep RL
00:18:19 |
Wed 10 Jun 2020
Alignment Newsletter #102: Meta learning by GPT-3, and a list of full proposals for AI alignment
00:17:28 |
Wed 03 Jun 2020
Alignment Newsletter #101: Why we should rigorously measure and forecast AI progress
00:19:51 |
Wed 27 May 2020
Alignment Newsletter #100: What might go wrong if you learn a reward function while acting
00:22:52 |
Wed 20 May 2020
Alignment Newsletter #99: Doubling times for the efficiency of AI algorithms
00:19:39 |
Wed 13 May 2020
Alignment Newsletter #98: Understanding neural net training by seeing which gradients were helpful
00:16:38 |
Wed 06 May 2020
Alignment Newsletter #97: Are there historical examples of large, robust discontinuities?
00:18:49 |
Wed 29 Apr 2020
Alignment Newsletter #95: A framework for thinking about how to make AI go well
00:20:44 |
Wed 15 Apr 2020
Alignment Newsletter #94: AI alignment as translation between humans and machines
00:12:49 |
Wed 08 Apr 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.