After five months of me (Buck) being slow at finishing up the editing on this, we’re finally putting out our inaugural Redwood Research podcast. I think it came out pretty well—we discussed a bunch of interesting and underdiscussed topics and I’m glad to have a public record of a bunch...
Highly capable AI systems might end up deciding the future. Understanding what will drive those decisions is therefore one of the most important questions we can ask. Many people have proposed different answers. Some predict that powerful AIs will learn to intrinsically pursue reward. Others respond by saying reward is...
tl;dr: A heavily-monitored internally deployed AI with sensitive access (e.g. to model weights) could bypass safety controls by asking a weakly-monitored external API version of itself (or another AI) what to do. It could then use its privileged access to execute instructions that the external API generated under less monitoring....
Last week, Thinking Machines announced Tinker. It’s an API for running fine-tuning and inference on open-source LLMs that works in a unique way. I think it has some immediate practical implications for AI safety research: I suspect that it will make RL experiments substantially easier, and increase the number of...
To prevent potentially misaligned LLM agents from taking actions with catastrophic consequences, you can try to monitor LLM actions - that is, try to detect dangerous or malicious actions, and do something about it when you do (like blocking the action, starting an investigation, …).[1] But where in your infrastructure...
The Alignment Project is a global fund of over £15 million, dedicated to accelerating progress in AI control and alignment research. It is backed by an international coalition of governments, industry, venture capital and philanthropic funders. This post is part of a sequence on research areas that we are excited...
One of our main activities at Redwood is writing follow-ups to previous papers on control like the original and Ctrl-Z, where we construct a setting with a bunch of tasks (e.g. APPS problems) and a notion of safety failure (e.g. backdoors according to our specific definition), then play the adversarial...