Alternative title: “When should you assume that what could go wrong, will go wrong?” Thanks to Mary Phuong and Ryan Greenblatt for helpful suggestions and discussion, and Akash Wasil for some edits. In discussions of AI safety, people often propose the assumption that something goes as badly as possible. Eliezer Yudkowsky in particular has argued for the importance of security mindset when thinking about AI alignment. I think there are several distinct reasons that this might be the right assumption to make in a particular situation. But I think people often conflate these reasons, and I think that this causes confusion and mistaken thinking. So I want to spell out some distinctions. Throughout this post, I give a bunch of specific arguments about AI alignment, including one argument that I think I was personally getting wrong until I noticed my mistake yesterday (which was my impetus for thinking about this topic more and then writing this post). I think I’m probably still thinking about some of my object level examples wrong, and hope that if so, commenters will point out my mistakes.Original text:https://www.lesswrong.com/posts/yTvBSFrXhZfL8vr5a/worst-case-thinking-in-ai-alignmentNarrated for AI Safety Fundamentals by Perrin Walker of TYPE III AUDIO.---A podcast by BlueDot Impact. Learn more on the AI Safety Fundamentals website.

Feedback is essential for learning. Whether you’re studying for a test, trying to improve in your work or want to master a difficult skill, you need feedback.The challenge is that feedback can often be hard to get. Worse, if you get bad feedback, you may end up worse than before.Original text:https://www.scotthyoung.com/blog/2019/01/24/how-to-get-feedback/Author: Scott YoungA podcast by BlueDot Impact. Learn more on the AI Safety Fundamentals website.

I’ve been obsessed with managing information, and communications in a remote team since Get on Board started growing. Reducing the bus factor is a primary motivation — but another just as important is diminishing reliance on synchronicity. When what I know is documented and accessible to others, I’m less likely to be a bottleneck for anyone else in the team. So if I’m busy, minding family matters, on vacation, or sick, I won’t be blocking anyone.This, in turn, gives everyone in the team the freedom to build their own work schedules according to their needs, work from any time zone, or enjoy more distraction-free moments. As I write these lines, most of the world is under quarantine, relying on non-stop video calls to continue working. Needless to say, that is not a sustainable long-term work schedule.Original text:https://www.getonbrd.com/blog/public-by-default-how-we-manage-information-visibility-at-get-on-boardAuthor: Sergio NouvelA podcast by BlueDot Impact. Learn more on the AI Safety Fundamentals website.

(In the process of answering an email, I accidentally wrote a tiny essay about writing. I usually spend weeks on an essay. This one took 67 minutes—23 of writing, and 44 of rewriting.)Original text:https://paulgraham.com/writing44.htmlAuthor:Paul GrahamA podcast by BlueDot Impact. Learn more on the AI Safety Fundamentals website.

This introduces the concept of Pareto frontiers. The top comment by Rob Miles also ties it to comparative advantage.While reading, consider what Pareto frontiers your project could place you on.Original text:https://www.lesswrong.com/posts/XvN2QQpKTuEzgkZHY/being-the-pareto-best-in-the-worldAuthor:John WentworthA podcast by BlueDot Impact. Learn more on the AI Safety Fundamentals website.

Learn how to succeed as an early-stage researcher by applying the Lean Startup Approach, crafting strong research project ideas, and navigating early-stage research through iteration and community engagement. Discover success strategies for researchers, including refining drafts, writing clearly, and collaborating effectively.

In this podcast, they discuss the importance of taking action to achieve goals and overcoming procrastination. They highlight the benefits of being a proactive agent who seizes opportunities and addresses challenges. It's a great reminder that planning alone is not enough for success.

Learn how to plan a high-impact career by aligning your values with global problems, creating long-term career hypotheses, and exploring strategic decision-making. Discover the importance of transferable career capital, managing uncertainties, and continuous career planning to ensure success and fulfillment.

This podcast provides a guide for those interested in working on AI alignment, covering career paths in the field, prerequisites for deep learning study, resources for AI alignment, and tips for navigating mental health in AI alignment work.

The podcast explores the impact of computing power on AI governance, discussing strategies for monitoring, resource allocation, and rule enforcement. It delves into the risks and feasibility of leveraging compute for governance in AI development, highlighting the implications for safety goals and civil liberties. The chapter also explores the role of compute in enhancing AI governance efforts and discusses challenges and limitations of using computing power as a regulatory tool for AI progress.