Sign up to save your podcasts
Or
Share BlueDot Narrated
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
BlueDot Narrated
BlueDot Narrated episodes
- Illustrating Reinforcement Learning from Human Feedback (RLHF)
Audio versions of blogs and papers from BlueDot courses.
This more technical article explains the motivations for a system like RLHF, and adds additional concrete details as to how the RLHF approach is applied to neural networks.
While reading, consider which parts of the technical implementation correspond to the 'values coach' and 'coherence coach' from the previous video.
A podcast by BlueDot Impact.
23 min - Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Audio versions of blogs and papers from BlueDot courses.
This paper explains Anthropic’s constitutional AI approach, which is largely an extension on RLHF but with AIs replacing human demonstrators and human evaluators.
A podcast by BlueDot Impact.
33 min - Constitutional AI Harmlessness from AI Feedback
Audio versions of blogs and papers from BlueDot courses.
This paper explains Anthropic’s constitutional AI approach, which is largely an extension on RLHF but with AIs replacing human demonstrators and human evaluators.
A podcast by BlueDot Impact.
1 hr 2 min - Introduction to Mechanistic Interpretability
Audio versions of blogs and papers from BlueDot courses.
Our introduction introduces common mech interp concepts, to prepare you for the rest of this session's resources.
Original text: https://aisafetyfundamentals.com/blog/introduction-to-mechanistic-interpretability/
Author(s): Sarah Hastings-WoodhouseA podcast by BlueDot Impact.
12 min - We Need a Science of Evals
Audio versions of blogs and papers from BlueDot courses.
This lays out a number of open questions, in what the author calls a 'Science of Evals'.
Original text: https://www.apolloresearch.ai/blog/we-need-a-science-of-evals
Author(s): Apollo Research blogA podcast by BlueDot Impact.
21 min - This is How AI Will Transform How Science Gets Done
Audio versions of blogs and papers from BlueDot courses.
This article by Eric Schmidt, former CEO of Google, explains existing use cases for AI in the scientific community and outlines ways that sufficiently advanced, narrow AI models might transform scientific discovery in the near future. As you read, pay close attention to the existing case studies he describes.Original text: https://www.technologyreview.com/2023/07/05/1075865/eric-schmidt-ai-will-transform-science/
Author(s): Eric SchmidtA podcast by BlueDot Impact.
11 min - If-Then Commitments for AI Risk Reduction
Audio versions of blogs and papers from BlueDot courses.
This article from Holden Karnofsky, now a visiting scholar at the Carnegie Endowment for International Peace, discusses "If-Then" commitments as a structured approach to managing AI risks without hindering innovation. These commitments offer a framework in which specific responses are triggered when particular risks arise, allowing for a proactive and organized approach to AI safety. The article emphasizes that as AI technology rapidly advances, such predefined voluntary commitments or regulatory requirements can help guide timely interventions, ensuring that AI developments remain safe and beneficial while minimizing unnecessary delays.Original text: https://carnegieendowment.org/research/2024/09/if-then-commitments-for-ai-risk-reduction?lang=en
Author(s): Holden KarnofskyA podcast by BlueDot Impact.
41 min - So You Want to be a Policy Entrepreneur?
Audio versions of blogs and papers from BlueDot courses.
This paper by academic Michael Mintrom defines policy entrepreneurs as "energetic actors who engage in collaborative efforts in and around government to promote policy innovations". He describes five methods they use: Problem framing, Using and expanding networks, Working with advocacy coalitions, Leading by example, and Scaling up change processes.Mintrom authored this piece focusing on the impacts of climate change, noting that it is an "enormous challenge now facing humanity", and that "no area of government activity will be immune from the disruptions to come". As you read, consider the ways in which AI governance parallels and contrasts with this framing.
Original text: https://www.tandfonline.com/doi/full/10.1080/25741292.2019.1675989
Author(s): Michael MintromA podcast by BlueDot Impact.
42 min - Open-Sourcing Highly Capable Foundation Models: An Evaluation of Risks, Benefits, and Alternative Methods for Pursuing Open-Source Objectives
Audio versions of blogs and papers from BlueDot courses.
This resource is the second of two on the benefits and risks of open-weights model release. In contrast, this paper expresses strong skepticism toward releasing highly capable foundation model weights, arguing that the risks may outweigh the benefits. While recognizing the advantages of openness, such as encouraging innovation and external oversight, it warns that making models publicly available increases the potential for misuse, including cyberattacks, biological weapon development, and disinformation. The article emphasizes that malicious actors could easily disable safeguards, fine-tune models for harmful purposes, and exploit vulnerabilities. Instead of fully open releases, it advocates for safer alternatives like democratic oversight, structured access, and staged model release, which can provide some benefits of openness while mitigating the extreme risks posed by advanced AI systems.Original text: https://cdn.governance.ai/Open-Sourcing_Highly_Capable_Foundation_Models_2023_GovAI.pdf
Author(s): Elizabeth Seger, Noemi Dreksler, Richard Moulange, Emily Dardaman, Jonas Schuett, K. Wei, Christoph Winter, Mackenzie Arnold, Seán Ó hÉigeartaigh, Anton Korinek, Markus Anderljung, Ben Bucknall, Alan Chan, Eoghan Stafford, Leonie Koessler, Aviv Ovadya, Ben Garfinkel, Emma Bluemke, Michael Aird, Patrick Levermore, Julian Hazell, Abhishek GuptaA podcast by BlueDot Impact.
57 min - Considerations for Governing Open Foundation Models
Audio versions of blogs and papers from BlueDot courses.
This resource is the first of two on the benefits and risks of open-weights model release. This paper broadly supports the open release of foundation model weights, arguing that such openness can drive competition, enhance innovation, and promote transparency. It contends that open models can distribute power more evenly across society, reducing the risk of market monopolies and fostering a diverse ecosystem of AI development. Despite potential risks like disinformation or misuse by malicious actors, the article argues that current evidence about these risks remains limited. It suggests that regulatory interventions might disproportionately harm developers, particularly if policies fail to account for the distinct benefits and challenges of open models compared to closed ones.Original text: https://hai.stanford.edu/sites/default/files/2023-12/Governing-Open-Foundation-Models.pdf
Author(s): Rishi Bommasani, Sayash Kapoor, Kevin Klyman, Shayne Longpre, Ashwin Ramaswami, Daniel Zhang, Marietje Schaake, Daniel E. Ho, Arvind Narayanan, Percy LiangA podcast by BlueDot Impact.
27 min
About BlueDot Narrated
From the publisher's feed
Audio versions of the core readings, blog posts, and papers from BlueDot courses.