Alignment Newsletter Podcast
By Rohin Shah et al.
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by Rohin Shah et al.
Category: Tech News
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 12
Reviews: 0
Episodes: 100
Description
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/
| Episode | Date |
|---|---|
|
Alignment Newsletter #173: Recent language model results from DeepMind
|
Jul 21, 2022 |
|
Alignment Newsletter #172: Sorry for the long hiatus!
|
Jul 05, 2022 |
|
Alignment Newsletter #171: Disagreements between alignment "optimists" and "pessimists"
|
Jan 23, 2022 |
|
Alignment Newsletter #170: Analyzing the argument for risk from power-seeking AI
|
Dec 08, 2021 |
|
Alignment Newsletter #169: Collaborating with humans without human data
|
Nov 24, 2021 |
|
Alignment Newsletter #168: Four technical topics for which Open Phil is soliciting grant proposals
|
Oct 28, 2021 |
|
Alignment Newsletter #167: Concrete ML safety problems and their relevance to x-risk
|
Oct 20, 2021 |
|
Alignment Newsletter #166: Is it crazy to claim we're in the most important century?
|
Oct 08, 2021 |
|
Alignment Newsletter #165: When large models are more likely to lie
|
Sep 22, 2021 |
|
Alignment Newsletter #164: How well can language models write code?
|
Sep 15, 2021 |
|
Alignment Newsletter #163: Using finite factored sets for causal and temporal inference
|
Sep 08, 2021 |
|
Alignment Newsletter #162: Foundation models: a paradigm shift within AI
|
Aug 27, 2021 |
|
Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity
|
Aug 20, 2021 |
|
Alignment Newsletter #160: Building AIs that learn and think like people
|
Aug 13, 2021 |
|
Alignment Newsletter #159: Building agents that know how to experiment, by training on procedurally generated games
|
Aug 04, 2021 |
|
Alignment Newsletter #158: Should we be optimistic about generalization?
|
Jul 29, 2021 |
|
Alignment Newsletter #157: Measuring misalignment in the technology underlying Copilot
|
Jul 23, 2021 |
|
Alignment Newsletter #156: The scaling hypothesis: a plan for building AGI
|
Jul 16, 2021 |
|
Alignment Newsletter #155: A Minecraft benchmark for algorithms that learn without reward functions
|
Jul 08, 2021 |
|
Alignment Newsletter #154: What economic growth theory has to say about transformative AI
|
Jun 30, 2021 |
|
Alignment Newsletter #153: Experiments that demonstrate failures of objective robustness
|
Jun 26, 2021 |
|
Alignment Newsletter #152: How we’ve overestimated few-shot learning capabilities
|
Jun 16, 2021 |
|
Alignment Newsletter #151: How sparsity in the final layer makes a neural net debuggable
|
May 19, 2021 |
|
Alignment Newsletter #150: The subtypes of Cooperative AI research
|
May 12, 2021 |
|
Alignment Newsletter #149: The newsletter's editorial policy
|
May 05, 2021 |
|
Alignment Newsletter #148: Analyzing generalization across more axes than just accuracy or loss
|
Apr 28, 2021 |
|
Alignment Newsletter #147: An overview of the interpretability landscape
|
Apr 21, 2021 |
|
Alignment Newsletter #146: Plausible stories of how we might fail to avert an existential catastrophe
|
Apr 14, 2021 |
|
Alignment Newsletter #145: Our three year anniversary!
|
Apr 07, 2021 |
|
Alignment Newsletter #144: How language models can also be finetuned for non-language tasks
|
Apr 02, 2021 |
|
Alignment Newsletter #143: How to make embedded agents that reason probabilistically about their environments
|
Mar 24, 2021 |
|
Alignment Newsletter #142: The quest to understand a network well enough to reimplement it by hand
|
Mar 17, 2021 |
|
Alignment Newsletter #141: The case for practicing alignment work on GPT-3 and other large models
|
Mar 10, 2021 |
|
Alignment Newsletter #140: Theoretical models that predict scaling laws
|
Mar 04, 2021 |
|
Alignment Newsletter #139: How the simplicity of reality explains the success of neural nets
|
Feb 24, 2021 |
|
Alignment Newsletter #138: Why AI governance should find problems rather than just solving them
|
Feb 17, 2021 |
|
Alignment Newsletter #137: Quantifying the benefits of pretraining on downstream task performance
|
Feb 10, 2021 |
|
Alignment Newsletter #136: How well will GPT-N perform on downstream tasks?
|
Feb 03, 2021 |
|
Alignment Newsletter #135: Five properties of goal-directed systems
|
Jan 27, 2021 |
|
Alignment Newsletter #134: Underspecification as a cause of fragility to distribution shift
|
Jan 21, 2021 |
|
Alignment Newsletter #133: Building machines that can cooperate (with humans, institutions, or other machines)
|
Jan 13, 2021 |
|
Alignment Newsletter #132: Complex and subtly incorrect arguments as an obstacle to debate
|
Jan 06, 2021 |
|
Alignment Newsletter #131: Formalizing the argument of ignored attributes in a utility function
|
Dec 31, 2020 |
|
Alignment Newsletter #130: A new AI x-risk podcast, and reviews of the field
|
Dec 24, 2020 |
|
Alignment Newsletter #129: Explaining double descent by measuring bias and variance
|
Dec 17, 2020 |
|
Alignment Newsletter #128: Prioritizing research on AI existential safety based on its application to governance demands
|
Dec 09, 2020 |
|
Alignment Newsletter #127: Rethinking agency: Cartesian frames as a formalization of ways to carve up the world into an agent and its environment
|
Dec 02, 2020 |
|
Alignment Newsletter #126: Avoiding wireheading by decoupling action feedback from action effects
|
Nov 26, 2020 |
|
Alignment Newsletter #125: Neural network scaling laws across multiple modalities
|
Nov 11, 2020 |
|
Alignment Newsletter #124: Provably safe exploration through shielding
|
Nov 04, 2020 |
|
Alignment Newsletter #123: Inferring what is valuable in order to align recommender systems
|
Oct 28, 2020 |
|
Alignment Newsletter #122: Arguing for AGI-driven existential risk from first principles
|
Oct 21, 2020 |
|
Alignment Newsletter #121: Forecasting transformative AI timelines using biological anchors
|
Oct 14, 2020 |
|
Alignment Newsletter #120: Tracing the intellectual roots of AI and AI alignment
|
Oct 07, 2020 |
|
Alignment Newsletter #119: AI safety when agents are shaped by environments, not rewards
|
Sep 30, 2020 |
|
Alignment Newsletter #118: Risks, solutions, and prioritization in a world with many AI systems
|
Sep 23, 2020 |
|
Alignment Newsletter #117: How neural nets would fare under the TEVV framework
|
Sep 16, 2020 |
|
Alignment Newsletter #116: How to make explanations of neurons compositional
|
Sep 09, 2020 |
|
Alignment Newsletter #115: AI safety research problems in the AI-GA framework
|
Sep 02, 2020 |
|
Alignment Newsletter #114: Theory-inspired safety solutions for powerful Bayesian RL agents
|
Aug 26, 2020 |
|
Alignment Newsletter #113: Checking the ethical intuitions of large language models
|
Aug 19, 2020 |
|
Alignment Newsletter #112: Engineering a Safer World
|
Aug 13, 2020 |
|
Alignment Newsletter #111: The Circuits hypotheses for deep learning
|
Aug 05, 2020 |
|
Alignment Newsletter #110: Learning features from human feedback to enable reward learning
|
Jul 29, 2020 |
|
Alignment Newsletter #109: Teaching neural nets to generalize the way humans would
|
Jul 22, 2020 |
|
Alignment Newsletter #108: Why we should scrutinize arguments for AI risk
|
Jul 15, 2020 |
|
Alignment Newsletter #107: The convergent instrumental subgoals of goal-directed agents
|
Jul 09, 2020 |
|
Alignment Newsletter #106: Evaluating generalization ability of learned reward models
|
Jul 01, 2020 |
|
Alignment Newsletter #105: The economic trajectory of humanity, and what we might mean by optimization
|
Jun 24, 2020 |
|
Alignment Newsletter #104: The perils of inaccessible information, and what we can learn about AI alignment from COVID
|
Jun 18, 2020 |
|
Alignment Newsletter #103: ARCHES: an agenda for existential safety, and combining natural language with deep RL
|
Jun 10, 2020 |
|
Alignment Newsletter #102: Meta learning by GPT-3, and a list of full proposals for AI alignment
|
Jun 03, 2020 |
|
Alignment Newsletter #101: Why we should rigorously measure and forecast AI progress
|
May 27, 2020 |
|
Alignment Newsletter #100: What might go wrong if you learn a reward function while acting
|
May 20, 2020 |
|
Alignment Newsletter #99: Doubling times for the efficiency of AI algorithms
|
May 13, 2020 |
|
Alignment Newsletter #98: Understanding neural net training by seeing which gradients were helpful
|
May 06, 2020 |
|
Alignment Newsletter #97: Are there historical examples of large, robust discontinuities?
|
Apr 29, 2020 |
|
Alignment Newsletter #96: Buck and I discuss/argue about AI Alignment
|
Apr 22, 2020 |
|
Alignment Newsletter #95: A framework for thinking about how to make AI go well
|
Apr 15, 2020 |
|
Alignment Newsletter #94: AI alignment as translation between humans and machines
|
Apr 08, 2020 |
|
Alignment Newsletter #93: The Precipice we’re standing at, and how we can back away from it
|
Apr 01, 2020 |
|
Alignment Newsletter #92: Learning good representations with contrastive predictive coding
|
Mar 25, 2020 |
|
Alignment Newsletter #91: Concepts, implementations, problems, and a benchmark for impact measurement
|
Mar 18, 2020 |
|
Alignment Newsletter #90: How search landscapes can contain self-reinforcing feedback loops
|
Mar 11, 2020 |
|
Alignment Newsletter #89: A unifying formalism for preference learning algorithms
|
Mar 04, 2020 |
|
Alignment Newsletter #88: How the principal-agent literature relates to AI risk
|
Feb 28, 2020 |
|
Alignment Newsletter #87: What might happen as deep learning scales even further?
|
Feb 20, 2020 |
|
Alignment Newsletter #86: Improving debate and factored cognition through human experiments
|
Feb 12, 2020 |
|
Alignment Newsletter #85: The normative questions we should be asking for AI alignment, and a surprisingly good chatbot
|
Feb 05, 2020 |
|
Alignment Newsletter #84: Reviewing AI alignment work in 2018-19
|
Jan 31, 2020 |
|
Alignment Newsletter #83: Sample efficient deep learning with ReMixMatch
|
Jan 22, 2020 |
|
Alignment Newsletter #82: How OpenAI Five distributed their training computation
|
Jan 15, 2020 |
|
Alignment Newsletter #81: Universality as a potential solution to conceptual difficulties in intent alignment
|
Jan 08, 2020 |
|
Alignment Newsletter #80: Why AI risk might be solved without additional intervention from longtermists
|
Jan 02, 2020 |
|
Alignment Newsletter #79: Recursive reward modeling as an alignment technique integrated with deep RL
|
Jan 01, 2020 |
|
Alignment Newsletter #78: Formalizing power and instrumental convergence, and the end-of-year AI safety charity comparison
|
Dec 26, 2019 |
|
Alignment Newsletter #77: Double descent: a unification of statistical theory and modern ML practice
|
Dec 19, 2019 |
|
Alignment Newsletter #76: How dataset size affects robustness, and benchmarking safe exploration by measuring constraint violations
|
Dec 04, 2019 |
|
Alignment Newsletter #75: Solving Atari and Go with learned game models, and thoughts from a MIRI employee
|
Nov 27, 2019 |
|
Alignment Newsletter #74: Separating beneficial AI into competence, alignment, and coping with impacts
|
Nov 20, 2019 |