BlueDot Narrated

Audio versions of blogs and papers from BlueDot courses.  In this post, we’ll present ARC’s approach to an open problem we think is central to aligning powerful machine learning (ML) systems:  Suppose we train a model to predict what the future will look like according to cameras and other sensors. We then use planning algorithms to find a sequence of actions that lead to predicted futures that lo...

Audio versions of blogs and papers from BlueDot courses.  We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through careful regularization. While this behavior appears to be fairly universal, we don’t yet full...

Audio versions of blogs and papers from BlueDot courses.  This post is about language model scaling laws, specifically the laws derived in the DeepMind paper that introduced Chinchilla. The paper came out a few months ago, and has been discussed a lot, but some of its implications deserve more explicit notice in my opinion. In particular: Data, not size, is the currently active constraint on langu...

Audio versions of blogs and papers from BlueDot courses.  (Sections 3.1-3.4 , 6.1-6.2 , and 7.1-7.5 ) Suppose we someday build an Artificial General Intelligence algorithm using similar principles of learning and cognition as the human brain. How would we use such an algorithm safely? I will argue that this is an open technical problem, and my goal in this post series is to bring readers with no p...

Audio versions of blogs and papers from BlueDot courses.  Gradient hacking is a hypothesized phenomenon where: A model has knowledge about possible training trajectories which isn’t being used by its training algorithms when choosing updates (such as knowledge about non-local features of its loss landscape which aren’t taken into account by local optimization algorithms). The model uses that knowl...

Audio versions of blogs and papers from BlueDot courses.  The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized an explicit model of the environment, combined with a specific planning algorithm (such as tree search...

Audio versions of blogs and papers from BlueDot courses. Abstract:  Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can't detect. We propose circumventing this issue by...

Audio versions of blogs and papers from BlueDot courses.  It would be very convenient if the individual neurons of artificial neural networks corresponded to cleanly interpretable features of the input. For example, in an “ideal” ImageNet classifier, each neuron would fire only in the presence of a specific visual feature, such as the color red, a left-facing curve, or a dog snout. Empirically, in...

Audio versions of blogs and papers from BlueDot courses.  This post tries to explain a simplified version of Paul Christiano’s mechanism introduced here , (referred to there as ‘Learning the Prior’) and explain why a mechanism like this potentially addresses some of the safety problems with naïve approaches. First we’ll go through a simple example in a familiar domain, then explain the problems wi...

Audio versions of blogs and papers from BlueDot courses.  This paper presents a technique to scan neural network based AI models to determine if they are trojaned. Pre-trained AI models may contain back-doors that are injected through training or by transforming inner neuron weights. These trojaned models operate normally when regular inputs are provided, and misclassify to a specific output label...

Audio versions of blogs and papers from BlueDot courses.  Using hard multiple-choice reading comprehension questions as a testbed, we assess whether presenting humans with arguments for two competing answer options, where one is correct and the other is incorrect, allows human judges to perform more accurately, even when one of the arguments is unreliable and deceptive. If this is helpful, we may...

Audio versions of blogs and papers from BlueDot courses.  Right now I’m working on finding a good objective to optimize with ML, rather than trying to make sure our models are robustly optimizing that objective. (This is roughly “outer alignment.”) That’s pretty vague, and it’s not obvious whether “find a good objective” is a meaningful goal rather than being inherently confused or sweeping key di...

Audio versions of blogs and papers from BlueDot courses. Previously, I argued that emergent phenomena in machine learning mean that we can’t rely on current trends to predict what the future of ML will be like. In this post, I will argue that despite this, empirical findings often do generalize very far, including across “phase transitions” caused by emergent behavior. This might seem like a contr...

Audio versions of blogs and papers from BlueDot courses. This article explains key drivers of AI progress, explains how compute is calculated, as well as looks at how the amount of compute used to train AI models has increased significantly in recent years. Original text: https://epochai.org/blog/compute-trends Author(s): Jaime Sevilla, Lennart Heim, Anson Ho, Tamay Besiroglu, Marius Hobbhahn, Pab...

Audio versions of blogs and papers from BlueDot courses. 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 a...

Audio versions of blogs and papers from BlueDot courses. 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/ho...

Audio versions of blogs and papers from BlueDot courses. 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...

Audio versions of blogs and papers from BlueDot courses. (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.html Author: Paul Graham A podcast by BlueDot Impact .

Audio versions of blogs and papers from BlueDot courses. 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-world Author: John Wentworth A podcast by BlueDot Imp...

Audio versions of blogs and papers from BlueDot courses. I am approaching the end of my AI governance PhD, and I’ve spent about 2.5 years as a researcher at FHI. During that time, I’ve learnt a lot about the formula for successful early-career research. This post summarises my advice for people in the first couple of years. Research is really hard, and I want people to avoid the mistakes I’ve made...

Audio versions of blogs and papers from BlueDot courses. The next four weeks of the course are an opportunity for you to actually build a thing that moves you closer to contributing to AI Alignment, and we're really excited to see what you do! A common failure mode is to think "Oh, I can't actually do X" or to say "Someone else is probably doing Y."  You probably can...

Audio versions of blogs and papers from BlueDot courses. We took 10 years of research and what we’ve learned from advising 1,000+ people on how to build high-impact careers, compressed that into an eight-week course to create your career plan , and then compressed that into this three-page summary of the main points. (It’s especially aimed at people who want a career that’s both satisfying and has...

Audio versions of blogs and papers from BlueDot courses. This guide is written for people who are considering direct work on technical AI alignment. I expect it to be most useful for people who are not yet working on alignment, and for people who are already familiar with the arguments for working on AI alignment. If you aren’t familiar with the arguments for the importance of AI alignment, you ca...

Audio versions of blogs and papers from BlueDot courses. This post summarises a new report, “Computing Power and the Governance of Artificial Intelligence.” The full report is a collaboration between nineteen researchers from academia, civil society, and industry. It can be read here . GovAI research blog posts represent the views of their authors, rather than the views of the organisation. Source...

Audio versions of blogs and papers from BlueDot courses. We’ve released a paper, AI Control: Improving Safety Despite Intentional Subversion . This paper explores techniques that prevent AI catastrophes even if AI instances are colluding to subvert the safety techniques. In this post: We summarize the paper; We compare our methodology to the methodology of other safety papers. Source: https://www....